## FANDOM

32.633 Seiten

125 gesichtete, geschützte Fragmente: Plagiat

 Bearbeitet: 7. January 2014, 15:57 SchumannErstellt: 26. July 2012, 05:18 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 149, Zeilen: 22-26
Quelle: Neal 2000
Seite(n): 261, 262, Zeilen: 28-29, 1-4
Following, a Gibbs sampling update is performed for cl in this representation of the posterior distribution. Since ci must be either one of the components associated with other observations or one of the auxiliary components that were introduced, we can easily do Gibbs sampling by evaluating the relative probabilities of these possibilities. Once a new value for cl has been chosen, we discard all values that are not associated with an observation. We now perform a Gibbs sampling update for ci in this representation of the posterior distribution. Since ci must be either one of the components associated with other

[Page 262]

observations or one of the auxiliary components that were introduced, we can easily do Gibbs sampling by evaluating the relative probabilities of these possibilities. Once a new value for ci has been chosen, we discard all ϕ values that are not now associated with an observation.

 Anmerkungen Dem Leser ist zwar klar, dass der Verfasser hier die Anwendung des Algorithmus 8 von Neal auf das untersuchte Problem beschreibt. Nicht klar ist allerdings, dass er dies mit den Worten Neals tut. Sichter (Hindemith), KnallErbse

 Bearbeitet: 7. January 2014, 15:29 SchumannErstellt: 28. July 2012, 11:08 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 148, Zeilen: 23-27, 29-32
Quelle: Chen et al. 2006
Seite(n): 7, 8, Zeilen: 7: 1-5; 8: 14-17
Let k- denote the number of represented mixtures. For represented mixtures, the previously derived conditional posteriors of (μl, Ωl) in (5.4.4) and (5.4.5) still hold. In contrast, in the absence of training data, the parameters in unrepresented mixtures are solely determined by their priors f(μl &#x007C ml, &#x03A3 / &#x03BA ) and f(Ω &#x007C &#x03BD1,&#x03C8-1). Thus the inference of the indicators, ci, must incorporate the effect of infinite mixtures. [...]

The conditional posteriors of (μl, Ωl)are Gaussian and Wishart distributions respectively, from which samples can be generated by using standard procedures. The sampling of the indicators requires the evaluation of the integral in equation (5.5.7), which is only analytically feasible if the conjugate prior is used.

Let krep denote the number of represented mixtures. For represented mixtures, the previously derived conditional posteriors of μj and &#x03C4j still hold (Eq. (4) and (5)). On the other hand, in the absence of training data, the parameters in unrepresented mixtures are

solely determined by their priors (p(μj &#x007C &#x03BB , &#x03B3 ) and p (&#x03C4j &#x007C &#x03B2 , &#x03C9 )), Thus the inference of the indicators, c, has to incorporate the effect of infinite mixtures.

[Seite 8]

The conditional posteriors of μj and &#x03C4j are Gaussian and Gamma distributions respectively, from which samples can be generated using standard procedures. The sampling of the indicators requires the evaluation of the integral in Eq. (12), which is only analytically feasible if the conjugate prior is used [...].

 Anmerkungen Ein Verweis auf die Quelle fehlt, obwohl es sich hier um eine fast wörtliche Übernahme handelt (nur die Notation wurde angepasst). Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 7. January 2014, 00:28 SchumannErstellt: 28. July 2012, 00:06 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 20, Zeilen: 7-8, 11-14
Quelle: Degen 2006
Seite(n): 11, Zeilen: 23-25, 26-29
2.2.4. Point processes in extreme value theory. The concept of exceedances over thresholds can be embedded into the theory of point processes in a natural way. [...] A detailed introduction to the theory of point processes would be beyond the aim of this thesis. For a concise introduction we therefore refer to Embrechts et al. (1997) and the references therein. For a more extensive survey we refer to Daley and Vere-Jones (2003). 1.4 Point Process of Exceedances

The concept of exceedances over thresholds can be embedded into the theory of point processes in a natural way. [...] A detailed introduction to the theory of point processes would be beyond the aim of this thesis. For a concise introduction we therefore refer to EKM [16] or Lindskog [26] and the references therein. For a more extensive survey we refer to Balkema and Embrechts [6].

 Anmerkungen No sign that the phrasing has been used, no reference to a source. "Embrechts et al. (1997)" = "EKM [16]" Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 7. January 2014, 00:23 SchumannErstellt: 28. July 2012, 11:42 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 14, Zeilen: 32-35
Quelle: Degen 2006
Seite(n): 5, Zeilen: 1-7
2.2.2. Domains of attraction. We say that a random variable X with distribution function F belongs to the maximum domain of attraction of an extreme value distribution H if relation (2.2.8) holds. In that case we write F ε MDA(H). We get the following characterizations of the maximum domain of attraction of an extreme value distribution H. 1.2 Domains of Attraction

We say that a random variable X (or its distribution function F) belongs to the maximum domain of attraction of an extreme value distribution H if relation (1.1) holds. In that case we write X ε MDA(H) (or F ε MDA(H)). As an immediate consequence of the Poisson approximation (see Appendix A) we get the following characterisation of the maximum domain of attraction of an extreme value distribution H:

 Anmerkungen keine Kennzeichnung der Übernahme, keine Quellenangabe Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 7. January 2014, 00:15 SchumannErstellt: 24. July 2012, 08:40 (Plagiatsfischer)

 Typus KomplettPlagiat Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 11, Zeilen: 7-10
Quelle: Embrechts et al. 1999b
Seite(n): 30, Zeilen: 5-10
The financial industry, including banking and insurance, is undergoing major changes. An increasing complexity of financial instruments calls for sophisticated risk management tools. Extreme value theory plays an important methodological role within risk management for insurance, reinsurance, and finance. The financial industry, including banking and insurance, is undergoing major changes. [...] An increasing complexity of financial instruments calls for sophisticated risk management tools. [...] Extreme value theory plays an important methodological role within risk management for insurance, reinsurance, and finance.
 Anmerkungen Wörtliche Übernahme mit Auslassung von zwei Sätzen. Ohne Quellenangabe. Sichter KnallErbse

 Bearbeitet: 23. August 2012, 11:08 HindemithErstellt: 29. July 2012, 21:23 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 140, Zeilen: 4-14
Quelle: Teh 2007
Seite(n): 2-3, Zeilen: S.2,33-38 - S.3,1-4
Definition 5.3.1. We say G is DP distributed with base distribution G0 and concentration parameter α, written G~DP(α,G0), if

(G(A1),...,G(Ar))~Dirichlet(αG0(A1),...,αG0(Ar)) (5.3.1)

for every finite measurable partition A1,...,Ar over some probability space Θ.

The parameters G0 and α play intuitive roles in the definition of the DP. The base distribution is basically the mean of the DP for any measurable set A⊂Θ, that is,

E[G(A)] = G0(A).

On the other hand, the concentration parameter can be interpreted as an inverse variance

${\scriptstyle \mathbb{V}[G(A)] = \frac{G_0(A)(1-G_0(A))}{\alpha + 1}.}$

The larger α is the smaller the variance and the DP will concentrate more of its mass around the mean.

[Seite 2]

We say G is Dirichlet process distributed with base distribution H and concentration parameter α, written G~DP(α,H), if

(G(A1),...,G(Ar))~Dir(αH(A1),...,αH(Ar)) (1)

for every finite measurable partition A1,...,Ar of Θ.

The parameters H and α play intuitive roles in the definition of the DP. The base distribution is basically the mean of the DP: for any measurable set A⊂Θ,

[Seite 3]

we have E[G(A)]=H(A). On the other hand, the concentration parameter can be understood as an inverse variance: V[G(A)]=H(A)(1-H(A))/(α + 1). The larger α is, the smaller the variance, and the DP will concentrate more of its mass around the mean.

 Anmerkungen Hier wurde nicht nur eine Definition übernommen, sondern auch große Teile der übrigen Darstellung (insbesondere die kommentierenden/erläuternden Zwischentexte). Dies wird sich im nächsten Fragment nahtlos fortsetzen, sodass sich Seite 140 im wesentlichen als Komplettübernahme von Material aus Teh (2007) erweist. Ein Hinweis darauf unterbleibt ebenso wie eine Kennzeichnung übernommener Formulierungen. Sichter (Graf Isolan), Hindemith

 Bearbeitet: 22. August 2012, 19:51 HindemithErstellt: 17. August 2012, 20:28 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 5, Zeilen: 41-42
Quelle: Hipp 2007
Seite(n): 7, Zeilen: 20-23
In brief, for multivariate distributions we can separate the marginals from the dependence

structure which is represented by the copula function. This leads to a two step modelling [of multivariate distributions: specify the marginals F1, ...,Fd and a copula function.]

This theorem states that for multivariate distributions we can separate the marginals from the dependence structure which is represented by the copula. This leads to a two step modeling of multivariate distributions: specify the marginals F1(x), ..., Fd(x) and a copula, [...]
 Anmerkungen Es handelt sich hier für Insider zwar um eine Banalität, trotzdem ist der Wortlaut speziell genug um hier eine Übernahme nachzuweisen. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 22. August 2012, 19:45 HindemithErstellt: 20. August 2012, 00:13 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 14, Zeilen: 8-11
Quelle: Schmidt 2003
Seite(n): 12, 13, Zeilen: 12: 37-39; 13: 19-21
This class of distributions provide us with techniques to trade off the bias of having insufficient data in practice and meaningful extrapolations beyond the range of given data. Frèchet [sic!] distributions are primarily applied in finance because of their unbounded support on the positive halfline and their relationship to so called heavy-tailed distributions. [Seite 12: 37-39]

EVT provides techniques to trade off the bias of having insufficient data in practice and meaningful extrapolations beyond the range of given data.

[Seite 13: 19-21]

Fréchet distributions (ξ > 0) are primarily applied in practice because of their unbounded support on the positive halfline and their relationship to so-called heavy-tailed distributions.

 Anmerkungen Die Quelle ist nicht genannt. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 22. August 2012, 19:43 HindemithErstellt: 19. August 2012, 23:56 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 5, Zeilen: 6-14
Quelle: Schmidt 2003
Seite(n): 5, 6, Zeilen: 5: 25-27; 6: 5-11
Indeed, standard portfolio selection is usually based on this approach, the Markowitz mean-variance theory and the Sharpe-Lintner-Mossin capital asset pricing model (CAPM). Further, the dependence structure of the asset returns is solely described by the Pearson correlation of the returns. This suffices in case the asset return distributions are multivariate normal. However, if we leave the Gaussian or more generally the elliptical world, a mere consideration of the correlation matrix often explains the dependence structure in a quite unsatisfying way. Pitfalls like a non-existing correlation or zero correlation for dependent random variables may occur. Especially the dependence structure of extreme events is usually poorly or incorrectly described by this measure. [Seite 5: 25-27]

Standard portfolio selection is usually based on the Markowitz mean-variance theory of risk and return, from 1952 on, and the Sharpe-Lintner-Mossin capital asset pricing model (CAPM) of 1964-66.

[Seite 6: 5-11]

In particular, the dependence structure of the asset returns is solely described by the covariance matrix Σ. This suffices in case the asset-return distributions are multivariate normal. However, if we leave the Gaussian world, a sole consideration of the covariance matrix often explains the dependence structure in a quite unsatisfying way. Pitfalls like a non-existing covariance or zero covariance for dependent random variables may occur. Especially the dependence structure of extreme events is usually poorly or incorrectly described by the covariance matrix.

 Anmerkungen Die Quelle ist nicht angegeben. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 22. August 2012, 18:42 HindemithErstellt: 22. July 2012, 23:07 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 6, Zeilen: 18-21
Quelle: Chavez-Demoulin_Embrechts_2010
Seite(n): 18, Zeilen: 3-6
Summarizing, extreme value theory offers a powerful and key theory for use in risk management. Indeed, just in few fields of application we have statistical quantities hard wired in the law, like VaR-based capital requirements within the Basel II regulatory framework for large international banks. Statistics offers a powerful and key theory for use in QRM. Indeed in very few fields of application do we have statistical quantities hard-wired in the law, like VaR–based capital requirements within the Basel II regulatory framework for large international banks; [...]
 Anmerkungen no source given Sichter (Hindemith), KnallErbse

 Bearbeitet: 22. August 2012, 17:52 HindemithErstellt: 20. August 2012, 00:19 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 22, Zeilen: 7-11
Quelle: Schmidt 2003
Seite(n): 14, Zeilen: 15-19
Summarizing the above results, univariate EVT provides probabilistic tools to model the limiting distributions of normalized maxima and excesses over high thresholds. Regarding the parameter estimation of extreme value distributions it suffices to apply parametric estimation methods instead of nonparametric estimation methods which are less robust for small sample sizes. Summarizing the above results, univariate EVT provides probabilistic tools to model the limiting distributions of normalized maxima and excesses over high thresholds. Regarding the parameter estimation of extreme value distributions it suffices to apply parametric estimation methods instead of nonparametric estimation methods which are less robust for small sample sizes.
 Anmerkungen Eine Quellenangabe fehlt für diese Übernahme, die mit "Summarizing the above results" beginnt, also das Unterkapitel zusammenfassen soll. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 22. August 2012, 17:51 HindemithErstellt: 17. August 2012, 00:37 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 2, Zeilen: 21-22
Quelle: Gencay Selcuk 2003
Seite(n): 4, Zeilen: 32-33
The normal distribution is the important limiting distribution for sample averages as summarized in a central limit theorem The normal distribution is the important limiting distribution for sample averages as summarized in a central limit theorem.
 Anmerkungen Das Fragment ist kurz, aber die Übereinstimmung ist 100%. Derselbe Satz findet sich in der Quelle Gencay et al. 2002 S. 3 Z. 32-33. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 22. August 2012, 17:51 HindemithErstellt: 16. August 2012, 00:05 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 85, Zeilen: 17-21
Quelle: Jalal Rockinger 2004
Seite(n): 1, Zeilen: 7-11
For instance, Jalal and Rockinger (2004) investigated the consequences for value at risk and expected short fall [sic] purposes of using a GARCH filter on various misspecified processes. They show that careful investigation of the adequacy of the GARCH filter is necessary since under misspecifications a GARCH filter appears to do more harm than good. We investigate the consequences for value-at-risk and expected shortfall purposes of using a GARCH filter on various mis-specified processes. We show that careful investigation of the adequacy of the GARCH filter is necessary since under mis-specifications a GARCH filter appears to do more harm than good.
 Anmerkungen Die Beschreibung der Arbeit von Jalal und Rockinger (2004) wird direkt aus dem Abstract der Publication übernommen, ohne dass dies kenntlich gemacht wäre. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 19. August 2012, 23:35 HindemithErstellt: 23. July 2012, 22:05 (Plagiatsfischer)

 Typus Verschleierung Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 1, Zeilen: 27-31
Quelle: Kole 2006
Seite(n): 1, Zeilen: 22-26
A crash is defined as an extreme event in a single asset, a single sector or a single market. We consider a crisis as a period with marked extreme dependence or comovements, which affect many assets in an industry, a single market or several markets worldwide. While a crash refers to a specific event in one asset, industry or market on its own, a crisis refers to a period of turmoil in several assets, industries or markets at the same time. Dependent on the aggregation level, we define a crash as a large price decrease of a single asset, a single sector or a single market. We consider a crisis as a period with high uncertainty that affects many assets in an industry, a single market or several markets worldwide. So while a crash refers to a specific event in one asset, industry or market on its own, a crisis refers to a period of turmoil in several assets, industries or markets at the same time.
 Anmerkungen Ohne Quellenangabe Sichter KnallErbse

 Bearbeitet: 18. August 2012, 20:24 HindemithErstellt: 28. July 2012, 12:09 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 15, Zeilen: 1-10
Quelle: Degen 2006
Seite(n): 5, Zeilen: 13-23
Theorem 2.2.5. (Characterization of MDAα(x)))

The distribution function F belongs to the maximum domain of attraction of Φα(x) (α>0) if and only if ${\scriptstyle \bar{F}(x)\in \mathcal{R}_{-\alpha}}$. In that case

an-1Mn $\xrightarrow{d}$ Φα

with ${\scriptstyle a_n = F^\leftarrow(1-1/n),}$ where ${\scriptstyle F^\leftarrow}$ is the quantile function.

Proof. See for instance Resnick (1987), Proposition 1.11, pp. 54. ${\scriptstyle\square}$

By Taylor expansion, we can see that 1-Φα(x)= 1-exp(-x) ~ x as ${\scriptstyle x\to\infty,}$ i.e., the tail of Φα decreases like a power law. At this point is where the concept of regular variation play [sic!] an important role. Indeed, regular variation tells us how far we can move from exact power law behaviour and still remain in MDAα(x)).

By Taylor expansion, 1-Φα(x)= 1-exp(-x) ~ x as ${\scriptstyle x\to\infty,}$ i.e. the tail of Φα decreases like a power law. At this point the concept of regular variation enters; see Appendix C. Regular variation tells us how far we can move from exact power law behavior and still remain in MDAα(x)). The following theorem traces back to Gnedenko (1943):

Theorem 1.2 (Characterization of MDAα(x)))

The df F belongs to the maximum domain of attraction of Φα(x) (α>0) if and only if ${\scriptstyle\bar{F}(x)\in RV_{-\alpha} }$. In that case

an-1Mn ${\scriptstyle\xrightarrow{d}}$ Φα

with ${\scriptstyle a_n = F^\leftarrow(1-1/n).}$

Proof. See for instance Resnick [34], pp. 54-57.${\scriptstyle \square}$

 Anmerkungen Keine Kennzeichnung der Übernahme, keine Quellenangabe. Wo Rh von der Vorlage abweicht, finden sich Grammatikfehler. Die Herkunft des Theorems, welche von Degen explizit gemacht wurde, wird bei Rh verschwiegen. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 18. August 2012, 20:20 HindemithErstellt: 30. July 2012, 11:29 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 140, Zeilen: 14-31
Quelle: Teh 2007
Seite(n): 4, Zeilen: 5-23
Now we are interested in the posterior distribution of G given some observed values. Let π1, ..., πn be a sequence of independent draws from G. Note that the πi's take values in Θ since G is a distribution over Θ. Let A1,...,Ar be a finite measurable partition of Θ, and let nk be the number of observed values in Ak. Then by the conjugancy [sic!] between the Dirichlet and the multinomial distributions, we have
(G(A1),...,G(Ar))│π1, ..., πn ~ Dir(αG0(A1)+n1, ..., αG0(Ar)+nr). (5.3.2)

Since the above is true for all finite measurable partitions, the posterior distribution over G must be a DP as well.

In fact, the posterior DP is

${\scriptstyle G\mid \pi_1,\dots,\pi_n\sim DP \left( \alpha+n,\frac{\alpha G_0 + \sum^n_{i=1}\delta_{\pi_i}}{\alpha+n}\right).}$

Notice that the DP has updated concentration parameter α+n and base distribution ${\scriptstyle\frac{\alpha G_0 + \sum^n_{i=1}\delta_{\pi_i}}{\alpha+n},}$ where δi is a point mass located at πi and ${\scriptstyle n_k = \sum^n_{i=1}\delta_{\pi_i}(A_k).}$ In other words, the DP provides a conjugate family of priors over distributions that are closed under posterior updates given observations.

Furthermore, notice that the posterior base distribution is weighted average between the prior base G0 and the empirical distribution ${\scriptstyle\frac{\sum^n_{i=1}\delta_{\pi_i}}{n}.}$ Indeed, the weight associated with the prior base distribution is proportional to α, while the empirical distribution has weight proportional to the number of observations n.

Let θ1, ..., θn be a sequence of independent draws from G. Note that the θi's take values in Θ since G is a distribution over Θ. We are interested in the posterior distribution of G given observed values of θ1, ..., θn. Let A1,...,Ar be a finite measurable partition of Θ, and let nk=#{i: θi ∈ Ak} be the number of observed values in Ak. By (1) and the conjugacy between the Dirichlet and the multinomial distributions, we have
(G(A1),...,G(Ar))│θ1, ..., θn ~ Dir(αH(A1)+n1, ..., αH(Ar)+nr). (2)

Since the above is true for all finite measurable partitions, the posterior distribution over G must be a DP as well. A little algebra shows that the posterior DP has updated concentration parameter α+n and base distribution ${\scriptstyle\frac{\alpha H + \sum^n_{i=1}\delta_{\theta_i}}{\alpha+n},}$ where δi is a point mass located at θi and ${\scriptstyle n_k = \sum^n_{i=1}\delta_i(A_k).}$ In other words, the DP provides a conjugate family of priors over distributions that is closed under posterior updates given observations. Rewriting the posterior DP, we have

${\scriptstyle G\mid \theta_1,\dots,\theta_n\sim DP\left(\alpha+n,\frac{\alpha}{\alpha+n}H + \frac{n}{\alpha+n} \frac{\sum^n_{i=1}\delta_{\pi_i}}{n}\right).}$ (3).

Notice that the posterior base distribution is a weighted average between the prior base distribution H and the empirical distribution ${\scriptstyle\frac{\sum^n_{i=1}\delta_{\theta_i}}{n}.}$ The weight associated with the prior base distribution is proportional to α, while the empirical distribution has weight proportional to the number of observations n.

 Anmerkungen keine Kennzeichnung der übernommenen Passagen, keine Quellenangabe; Sichter (Graf Isolan), Hindemith

 Bearbeitet: 15. August 2012, 23:52 HindemithErstellt: 27. July 2012, 16:48 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 128, Zeilen: 22-26
Quelle: Zhang 2008
Seite(n): 1, Zeilen: 9-13
Unfortunately, there is an infinite number of parameters in the definition of M4 processes, which poses challenges in statistical applications where workable models are preferred. Recently Zhang (2008) established sufficient conditions under which an M4 process with infinite number of parameters may be approximated by an M4 process with finite number of parameters. There is an infinite number of parameters in the definition of multivariate maxima of moving maxima (M4) processes, which poses challenges in statistical applications where workable models are preferred. This paper establishes sufficient conditions under which an M4 process with infinite number of parameters may be approximated by an M4 process with finite number of parameters.
 Anmerkungen Für die Zusammenfassung der Arbeit Zhangs wird der Abstract dieser Arbeit herangezogen, ohne dass dies gesagt würde. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 15. August 2012, 22:20 HindemithErstellt: 14. August 2012, 04:05 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 16, Zeilen: 1-19
Quelle: Lindskog 2004
Seite(n): 10, 11, Zeilen: -
EXAMPLE 2.2.9. (Maxima of Cauchy random variables). Let X be a sequence of iid standard Cauchy random variables, i.e. the density function is given by ${\scriptstyle f(x) = \frac{1}{\pi(1+x^2)} }$ for ${\scriptstyle x \in \mathbb{R} }$. Using l’Hospitals rule we obtain
${\scriptstyle \lim_{x\to\infty}\frac{\bar{F}(x)}{(\pi x)^{-1} }= \lim_{x\to\infty}\frac{f(x)}{\pi^{-1} x^{-2} } = }$
${\scriptstyle \lim_{x\to\infty}\frac{\pi x^2}{\pi (1+ x^2) }=1 }$

Then ${\scriptstyle \bar{F}(x)\sim(\pi x)^{-1} }$ as ${\scriptstyle x\to\infty}$. Hence, for ${\scriptstyle x>0, \quad\bar{F}(nx/\pi)\sim (nx)^{-1} }$ as ${\scriptstyle n\to\infty}$ and

${\scriptstyle \mathbb{P} (M_n\le nx/\pi ) = \left(1- \bar{F} (nx/\pi)\right)^n }$
${\scriptstyle = \left( 1-\frac{1}{n}\left(\frac{1}{x} + o(1)\right)\right)^n }$
${\scriptstyle \to \quad \exp\left\{ -x^{-1}\right\}= \Phi_1 (x), }$

for ${\scriptstyle x>0}$. Hence F belongs to the maximum domain of attraction of the Frèchet [sic] distribution. The normalizing constants can be chosen to be ${\scriptstyle a_n=n }$ and ${\scriptstyle b_n=0 }$

EXAMPLE 2.2.10. (Maxima of exponential random variables). Let X be a sequence of iid standard exponential random variables, i.e., the distribution function F of X is given by ${\scriptstyle F(x) = 1- e^{-x} }$ for ${\scriptstyle x\ge 0 }$ Then,

${\scriptstyle \mathbb{P} (M_n - \ln n\le x ) = F( x+\ln n)^n }$
${\scriptstyle = (1-\exp(-x-\ln n ))^n }$
${\scriptstyle = (1-n^{-1} e^{-x} )^n }$
${\scriptstyle \to \quad \exp ( -e^x )= \Lambda (x) , \quad x\in\mathbb{R} }$

Hence, F belongs to the maximum domain of attraction of the Gumbel distribution. The normalizing constants can be chosen to be ${\scriptstyle a_n=1 }$ and ${\scriptstyle b_n= \ln n }$

Example 3.2 (Maxima of exponential random variables). Let (Xk) be a sequence of iid standard exponential random variables, i.e. the distribution function F of Xk is given by${\scriptstyle F(x) = 1- e^{-x} }$ for ${\scriptstyle x\ge 0 }$ Then
${\scriptstyle \mathbb{P} (M_n - \ln n\le x ) = F( x+\ln n)^n }$
${\scriptstyle = (1-\exp\{-x-\ln n\})^n }$
${\scriptstyle = (1-n^{-1} e^{-x} )^n }$
${\scriptstyle \to \quad \exp \{-e^{-x}\} = \Lambda (x) , \quad x\in\mathbb{R} }$

Hence, F belongs to the maximum domain of attraction of the Gumbel distribution ${\scriptstyle (F \in MDA(\Lambda))}$. The normalizing constants can be chosen to be ${\scriptstyle a_n=1 }$ and ${\scriptstyle b_n= \ln n }$.

Example 3.3 (Maxima of Cauchy random variables). Let (Xk) be a sequence of iid standard Cauchy random variables, i.e. the density function f of Xk is given by ${\scriptstyle f(x) = (\pi(1+x^2))^{-1} }$ for ${\scriptstyle x \in \mathbb{R} }$. Using l’Hospitals rule we obtain

${\scriptstyle \lim_{x\to\infty}\frac{\bar{F}(x)}{(\pi x)^{-1} }= \lim_{x\to\infty}\frac{f(x)}{\pi^{-1} x^{-2} } = }$
${\scriptstyle \lim_{x\to\infty}\frac{\pi x^2}{\pi (1+ x^2) }=1 }$

i.e. ${\scriptstyle \bar{F}(x)\sim(\pi x)^{-1} }$ as ${\scriptstyle x\to\infty}$. Hence, for ${\scriptstyle x>0, \quad\bar{F}(nx/\pi)\sim (nx)^{-1} }$ as ${\scriptstyle n\to\infty}$ and

${\scriptstyle \mathbb{P} (M_n\le \frac{nx}{\pi}) = \left( 1- \bar{F}\left(\frac{nx}{\pi}\right)\right)^n }$
${\scriptstyle = \left( 1-\frac{1}{n}\left(\frac{1}{x} + o(1)\right)\right)^n }$
${\scriptstyle \to \quad \exp\left\{ -x^{-1}\right\}= \Phi_1 (x), \quad x > 0. }$

[Seite 11]

For ${\scriptstyle x\le 0, \mathbb{P}(M_n\le nx/\pi )\le F (0)^n \to 0 }$. Hence, F belongs to the maximum domain of attraction of the Fréchet distribution ${\scriptstyle (F \in MDA(\Phi_1))}$. The normalizing constants can be chosen to be ${\scriptstyle a_n=n/\pi }$ and ${\scriptstyle b_n=0 }$.

 Anmerkungen Ausser der Reihenfolge der Beispiele sind die Unterschiede zwischen Quelle und Dissertation sehr gering: es gibt in der Dissertation geringfügige Auslassungen und eine fehlerhafte Normalisierungskonstante. Es mag sich hier zwar um Standardbeispiele handeln, aber der Wortlaut und die mathematische Herleitung Term für Term sind übernommen ohne dass die Quelle genannt wird. Sichter (Hindemith), WiseWoman

 Bearbeitet: 15. August 2012, 22:17 HindemithErstellt: 9. August 2012, 21:16 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 16, Zeilen: 20-22
Quelle: Boldi 2004
Seite(n): 20, Zeilen: 23-25
In practice, the estimation $\xi \in \mathbb{R}, \psi>0, \mu \in \mathbb{R}$ in (2.2.9) requires one to decompose the sample into blocks and take the blockwise maxima. A drawback with this approach is the loss of data. In practice, the estimation of μ, σ and κ requires one to decompose the sample into blocks and take the blockwise maxima. A drawback with this approach is the loss of data.
 Anmerkungen Ein Quellenverweis fehlt. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 15. August 2012, 21:53 HindemithErstellt: 14. August 2012, 05:55 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 12, Zeilen: 26-28
Quelle: Lindskog 2004
Seite(n): 6, Zeilen: 7-9
First of all it is essential to know under what conditions of F there is a nontrivial limit of ${\scriptstyle \mathbb{P}(M_n \le x) }$ as ${\scriptstyle n\to\infty }$ for appropriate sequences of constants un. First of all it is essential to know under what conditions on F there is a nontrivial limit of ${\scriptstyle \mathbb{P}(M_n \le u_n) }$ as ${\scriptstyle n\to\infty }$ for appropriate sequences of constants un.
 Anmerkungen Die Fundstelle ist zwar nur kurz, die Textübernahme aber eindeutig. Sowohl in der Dissertation als auch in der Quelle folgt auf diese Stelle der Satz über die Poisson-Approximation in sehr ähnlichem Wortlaut. Bemerkenswert ist auch, dass in der Dissertation von "for appropriate sequences of constants un" die Rede ist, diese sequences aber davor nirgends erwähnt werden. Die Quelle ist hier wohl korrekt. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 15. August 2012, 21:49 HindemithErstellt: 15. August 2012, 15:11 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 146, Zeilen: 18-23
Quelle: Rasmussen 2000
Seite(n): 557, Zeilen: 17-21
Note as the results in (5.5.6) and (5.5.7) show that the conditional class prior for classes that are associated with observations other than yl is proportional to the number of such observations and that the combined prior for all other classes depends only on α and l'.

The main advantage of this representation is that it allows us to work with the finite number of indicators cl, rather than the infinite number of mixing proportions, which is crucial for the estimation of this class of processes.

This shows that the conditional class prior for components that are associated with other observations is proportional to the number of such observations; the combined prior for all other classes depends only on α and n. Notice how the analytical tractability of the integral in eq. (12) is essential, since it allows us to work directly with the (finite number of) indicator variables, rather than the (infinite number of) mixing proportions.
 Anmerkungen Man beachte auch, dass die Gleichungen: 5.5.4 - 5.5.7, die vor der hier dokumentierten Stelle in der Dissertation zu finden sind, auch in der Quelle stehen. Außerdem sei darauf hingewiesen, dass auf Seite 144 der Dissertation (vor dem Unterkapitel, das die hier dokumentierte Stelle enthält) folgender Satz steht: "The univariate development in Escobar and West (1995) and Rasmussen (2000) can be extended and modified to produce various methods of estimation described below." Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 15. August 2012, 11:53 HindemithErstellt: 10. August 2012, 13:47 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 23, Zeilen: 18-23
Quelle: Fougères 2004
Seite(n): 4, Zeilen: 7-14
EXAMPLE 2.3.1. Consider a multivariate Gaussian distribution, with all univariate marginals equal to N(0, 1), and with all its correlations less than 1. Such a distribution is in the domain of attraction of the independence with univariate Gumbel marginals. Indeed, one has that
${\scriptstyle F^n \left( {\mathbf a}_n {\mathbf x} + {\mathbf b}_n \right) \rightarrow G({\mathbf x})= \prod^d_{j=1} \exp \left\{ -e^{-x_j} \right\} }$

The norming constants are respectively equal to ${\scriptstyle {\mathbf a}_n = (2 \log n)^{-1 /2} }$ and ${\scriptstyle {\mathbf b}_n = b_n {\mathbf 1} }$, where ${\scriptstyle b_n = ( 2 \log n )^{1/2} - 1/2 ( \log \log n + \log 4\pi ) / ( 2 \log n )^{- 1 / 2} }$ , and ${\scriptstyle {\mathbf 1} = ( 1 , \ldots , 1)}$.

Example 1 (i) Consider the multivariate normal d.f. FN with all univariate margins equal to N(0 ,1), and with all its correlations less than 1 [...]. Such a distribution is in the domain of attraction of the independence with univariate Gumbel margins (Sibuya, 1960). Indeed, one has that
${\scriptstyle F^n_N \left( a_n {\mathbf x} + {\mathbf b}_n \right) \rightarrow G({\mathbf x})= \prod^d_{j=1} \exp \left\{ -e^{-x_j} \right\} }$

The norming constants are respectively equal to ${\scriptstyle a_n = (2 \log n)^{-1 /2} }$ and ${\scriptstyle {\mathbf b}_n = b_n {\mathbf 1} }$, where ${\scriptstyle b_n = ( 2 \log n )^{1/2} - 1/2 ( \log \log n + \log 4\pi ) / ( 2 \log n )^{1 / 2} }$ , and ${\scriptstyle {\mathbf 1} = ( 1 , \ldots , 1)}$. (see for example Resnick (1987), Example 2).

 Anmerkungen Das gesamte Beispiel ist aus der Quelle (oder auch von Resnick (1987)) übernommen, ohne dass dies angegeben wäre. In der Quelle finden sich Verweise auf die Originalquellen. Man beachte auch, dass in der Dissertation an als Vektor gekennzeichnet ist, was in der Quelle anders ist und auch keinen Sinn machen würde. Auch ist ein Minuszeichen anders in der Dissertation. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 15. August 2012, 11:51 HindemithErstellt: 8. August 2012, 00:57 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 158, Zeilen: 28-30
Quelle: Zhang Huang 2006
Seite(n): 6, Zeilen: 24-25
In general, M4 process models cannot be directly fitted to observed data since the data is not in unit Frèchet [sic] scales. Certain scale transformation is needed. In general, M4 process models can not be directly fitted to observed data since the data is not in unit Fréchet scales. Certain scale transformation is needed.
 Anmerkungen Wörtliche Übernahme ohne Quellenverweis. Kurz, aber eindeutig Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 15. August 2012, 11:29 HindemithErstellt: 8. August 2012, 01:07 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 159, Zeilen: 6-13
Quelle: Zhang Huang 2006
Seite(n): 6, 7, 8, Zeilen: 6: 22-24; 7:8-9; 8:3-5
The negative log returns, the estimated standard deviations and the standardized residuals are drawn in Figure 5.B.I. From the plots, clearly we see that there are extreme observations, jumps in returns, jumps in volatilities in each sequence.

One can observe that the devolatilized time series now looks stationary. However, jumps in returns are still persistent.

Second stage: transformation to Frèchet [sic] scale. The next step is to fit a generalized Pareto distribution (GPD) to exceedances over a specified threshold value, [...].

The negative log returns are plotted in Figure 1. From the plots, clearly we see that there are extreme observations, jumps in returns, jumps in volatilities in each sequence. [...]

[Seite 7]

One can see that the devolatilized time series now looks stationary. Jumps in returns are still persistent. [...]

[Seite 8]

The next step is to fit a generalized extreme value (GEV) distribution to the pseudo-observations or a generalized Pareto distribution (GPD) to exceedances over a specified threshold value.

 Anmerkungen Die Quelle wird nicht genannt. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 15. August 2012, 11:20 HindemithErstellt: 14. August 2012, 06:21 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 13, Zeilen: 7-11
Quelle: Lindskog 2004
Seite(n): 6, Zeilen: 27-31
It is also important to know whether there can be sequences of constants ${\scriptstyle a_n, \tilde{a}_n > 0}$ and ${\scriptstyle b_n, \tilde{b}_n \in \mathbb{R} }$ such that ${\scriptstyle a_n^{-1} (M_n - b_n )}$ and ${\scriptstyle \tilde{a}_n^{-1} (M_n - b_n )}$ converge in distribution to two different random variables with very different distributions ${\scriptstyle H}$ and ${\scriptstyle \tilde{H} }$. Fortunately, the following result states that any two possible such distribution functions ${\scriptstyle H}$ and ${\scriptstyle \tilde{H} }$ are closely linked. It is also important to know whether there can be sequences of constants ${\scriptstyle a_n, \tilde{a}_n > 0}$ and ${\scriptstyle b_n, \tilde{b}_n \in \mathbb{R} }$ such that ${\scriptstyle a_n^{-1} (M_n - b_n )}$ and ${\scriptstyle \tilde{a}_n^{-1} (M_n - \tilde{b}_n )}$ converge in distribution to two different random variables with very different distributions${\scriptstyle H}$ and ${\scriptstyle \tilde{H} }$. Fortunately, the following result states that any two possible such distribution functions ${\scriptstyle H}$ and ${\scriptstyle \tilde{H} }$ are closely linked.
 Anmerkungen Der einzige Unterschied zwischen Quelle und Dissertation ist eine fehlende Tilde in der Dissertation. Dieser Einleitung folgt dann sowohl in der Quelle als auch in der Dissertation in fast identischem Wortlaut das "Convergence of types theorem". Vor dieser Einleitung findet sich sowohl in der Dissertation als auch in der Quelle ein Satz zur Poisson-Approximation und dessen Beweis, wobei in der Dissertation dieser Beweis gekürzt ist. Sichter (Hindemith), WiseWoman

 Bearbeitet: 14. August 2012, 11:02 HindemithErstellt: 27. July 2012, 13:07 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 182, Zeilen: 9-15
Quelle: Wendin 2004
Seite(n): 10, 11, Zeilen: 36-39; 1-3
The characterization of multivariate regular variation in (6.3.1) is referred to as the sequential definition of regular variation (see Embrechts et al. (1997)) and it describes dependence among the marginals, while (6.3.2) rules out tails that are not regular varying. It is interesting to note that whereas univariate regular variation has been introduced as a function property, all the characterizations of multivariate regular variation are in terms of measures. Multivariate distribution functions are de facto more difficult to deal with than univariate distribution functions and therefore measures appear more natural. The characterization of multivariate regular variation in (ii) is referred to as the sequential definition of regular variation or the Feller definition of regular variation*. It is interesting to note that whereas univariate regular variation has been introduced as a function property, both characterizations of multivariate regular

[Seite 11]

variation in Theorem 1.1 are in terms of measures. Multivariate distribution functions are de facto more difficult to deal with than univariate distribution functions and therefore measures appear more natural.

• See Section VIII.8 of Feller vol II [10].
 Anmerkungen Bis auf einen kurzen Einschub weitgehend wörtlich der Quelle entnommen. Ein Quellenverweis fehlt. Sichter (Hindemith), KnallErbse

 Bearbeitet: 13. August 2012, 07:52 HindemithErstellt: 31. July 2012, 23:54 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 89, Zeilen: 18-23
Quelle: Smith 1994
Seite(n): 233, Zeilen: 10
Returning to the multivariate case there are several different but equivalent characterizations of multivariate extreme value distributions, see for examples the books of Resnick (1987), Falk et al. (2004) and Galambos (1978). One feature of multivariate extreme value distributions is that, the dependence structure is preserved under transformations of the marginal distributions, so there is no loss of generality in restricting attention to a particular univariate extreme value family. For this reason we assumed unit Frèchet [sic] marginals. There are several different but equivalent characterizasion of multivariate extreme value distributions, reviewed in detail in the books of Resnick (1987) und Galambos (1987). One feature of multivariate extreme value distribution is that the dependence structure is preserved under transformations of the marginal distributions, so there is no loss of generality in restricting attention to a particular univariate extreme value family. For example, de Haan and Resnick (1977) assumed unit Fréchet [...] margins and developed the charactisation [...]
 Anmerkungen Kein Quellenverweis vorhanden. Sichter (Hindemith), WiseWoman

 Bearbeitet: 11. August 2012, 20:58 WiseWomanErstellt: 8. August 2012, 11:52 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 97, Zeilen: 10-33
Quelle: Daley VereJones 2003
Seite(n): 231, 248, 249, Zeilen: 231: 12-17; 248: 38; 249: 1-3, 6-25
The main aim of the Proposition 4.3.14 was to make conditional the distribution of the current marks as time progresses, on marks and time points of all preceding events, i.e., the full set of the time points (0, T), irrespective of the marks and their relative positions in time.

Another view to look at is through the hazard functions. Instead of specifying the conditional densities pn(∙∣∙) as in (4.3.10) we express them in terms of their hazard functions

[GLEICHUNGEN, identisch zur Quelle, siehe link ]

Using the conditioning in the hazard functions may now include the values of the preceeding marks as well as the length of the current and preceeding intervals. Thus, all the information is summarized in the internal history H ≡ {Ht : t ≥ 0} of the process and of this form the amalgam of hazard function functions [sic] and mark densities can be represented as a single composite function for the MPP as follows

[GLEICHUNG, identisch zur Quelle, siehe link ]

where h1(t) is the hazard function for the location of the initial point, h2(t∣(t1, x1)) the hazard function for the location of the second point conditioned by the location of the first point and the value of the first mark, and so on, while f1(x∣t) is the density for the first mark given its location, and so on.

Hence a regular MPP N on R+ × X can be represented piecewise by the function λ*(t, x) named the conditional intensity function with respect to its internal history H.

Predictability, as it was defined in (4.3.5), is important in it that the hazard functions refer to the risk at the end of a time interval, not at the beginning of the next interval.

[Seite 248: 38]

In the equations above we condition the distribution of the current mark, as

[Seite 249: 1-3]

time progresses, on both marks and time points of all preceding events; in the proposition, we condition on the full set of time points in (0, T), irrespective of the marks and of their relative positions in time.

[Seite 231: 12-17]

We now make a seemingly innocuous but critical shift of view. Instead of specifying the conditional densities pn(∙∣∙) directly, we express them in terms of their hazard functions

[GLEICHUNGEN, siehe (7.2.2) ]

[Seite 249: 6-25]

The conditioning in the hazard functions may now include the values of the preceding marks as well as the length of the current and preceding intervals. All this information is collected into the internal history H ≡ {Ht : t ≥ 0} of the process so that the amalgam of hazard functions and mark densities can be represented as a single composite function for the MPP, namely

[GLEICHUNG, siehe (7.3.2) ]

where h1(t) is the hazard function for the location of the initial point, h2(t∣(t1, κ1)) the hazard function for the location of the second point conditioned by the location of the first point and the value of the first mark, and so on, while f1(κ∣t) is the density for the first mark given its location, and so on.

Definition 7.3.II. Let N be a regular MPP on R+ × K. The conditional intensity function for N, with respect to its internal history H, is the representative function λ*(t, κ) defined piecewise by (7.3.2).

Predictability is again important in that the hazard functions refer to the risk at the end of a time interval, not at the beginning of the next time interval, [...]

 Anmerkungen Ein Quellenverweis fehlt. Sichter (Hindemith), WiseWoman

 Bearbeitet: 11. August 2012, 20:46 WiseWomanErstellt: 8. August 2012, 00:14 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith, Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 96, Zeilen: 11-32
Quelle: Daley VereJones 2003
Seite(n): 229, 247, 248, Zeilen: 229: 13-14, 25-29, 21; 247: 40-42; 248: 1, 4-11, 25-34
PROPOSITION 4.3.13 [siehe Link ]

The essence of the approach for the likelihood of a MPP is the use of a causal description of the process through successive conditioning. For ease of writing, we use jn(t1,..., tn ∣ w) for the local Janossy density on the interval (0,w) and J0(w) for J0((0,k)) [sic, recte: J0((0,w))]. Furthermore, we define the intervals τi = ti — ti-1 for i ≥ l and t0 = 0, and the conditional survivor functions Sk(w ∣ t1,..., tk−1) = P(τk ∣t1,..., tk−1) [sic, recte: P(τk > w ∣t1,..., tk−1)] and observe that these can be represented recursively in terms of the Janossy functions through the equations

[GLEICHUNGEN, identisch zur Quelle, siehe hier ]

where the pi (∙) are the densities, suitably conditioned, for the locations in the ground process, and the fi (∙) refer to the densities, again suitably conditioned, for the marks.

[Seite 247]

Proposition 7.3.I. [siehe Link ]

[Seite 229, 13-14]

The essence of this approach is the use of a causal description of the process through successive conditionings.[...]

[Seite 229, 25-26]

For ease of writing, we use jn(t1,..., tn ∣ u) for the local Janossy density on the interval (0,u), and J0(u) for J0((0,u)).

[Seite 229, 21]

[...] the intervals τi = ti — ti-1, i ≥ l, t0 = 0, are taken [...]

[Seite 229, 27-29] Now introduce the conditional survivor functions Sk(u ∣ t1,..., tk−1) = Pr{τk > u ∣t1,..., tk−1} and observe that these can be represented recursively in terms of the (local) Janossy functions through the equations

[Seite 248]

[GLEICHUNGEN, siehe link ]

where the pi (∙) refer to the densities, suitably conditioned, for the locations in the ground process, and the fi (∙) refer to the densities, again suitably conditioned, for the marks.

 Anmerkungen Die PROPOSITION 4.3.13 in der Dissertation ist identisch zur Proposition 7.3.I. in der Quelle (wobei in der Dissertation eine äquivalente Aussage weggelassen wurde). Ein Quellenverweis fehlt und auch nach der Proposition wird weiter übernommen. Dabei wird die Notation geringfügig geändert (u aus der Quelle wird zu w), wobei sich Fehler einschleichen (k anstatt w; > w vergessen). Sichter (Hindemith), (Plagiatsfischer), WiseWoman

 Bearbeitet: 11. August 2012, 20:11 WiseWomanErstellt: 7. August 2012, 22:30 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 91, Zeilen: 25-29
Quelle: Last Brandt 1995
Seite(n): 4, Zeilen: 7-13
Example 4.3.2. Suppose that t1,t2 — t1,t3 — t2,... are independent and distributed according to an exponential distribution with parameter λ. Then N(t) := ∑i≥1 I{ti≤t} is called a homogeneous Poisson process with intensity λ.

Given a univariate point process {tn}, one often has additional information on the points tn. It is modelled by a random element Xi which is called the mark of tn.

Example 1.2.2 Poisson process. Suppose that T1, T2 — T1, T3 — T2, ... are independent and distributed according to an exponential distribution with parameter λ > 0. Then Φ = (Tn)n≥1 = (Tn) is called a homogeneous Poisson process with intensity λ.

Given a univariate point process (Tn), one often has additional information on the points Tn. It is modeled by a random element Xn which is called the mark of Tn.

 Anmerkungen Ein Quellenverweis fehlt. Das Beispiel mag noch ein Standardbeispiel sein, die erklärenden Sätze nach dem Beispiel sind aber auch wörtlich übernommen. Sichter (Hindemith), WiseWoman

 Bearbeitet: 11. August 2012, 19:53 WiseWomanErstellt: 29. July 2012, 09:35 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 137, Zeilen: 1
Quelle: Hoffman et al. 2008
Seite(n): 2 (Exzerpt), Zeilen: -
 Anmerkungen Die Grafik sowie, abgesehen vom ersten Satz, auch die Beschreibung derselben stammen aus der Quelle. Ein Verweis auf diese fehlt aber. Das hier gewählte Beispiel für den "Chinese Restaurant Process" ist nur eines von vielen denkbaren ähnlichen Beispielen. Sichter (Hindemith), WiseWoman

 Bearbeitet: 11. August 2012, 19:41 WiseWomanErstellt: 31. July 2012, 18:00 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 138, Zeilen: 2-8
Quelle: Blei 2007
Seite(n): 1, Zeilen: 17ff
Thus, the l-th customer chooses a new unoccupied table with probability α/L — 1 + α, and an occupied table with probability nl/L — 1 + α, where nl is the number of people sitting at the table l. In the above, α is a scalar parameter of the process. One might acknowledge that the above does define a probability distribution. Let us denote by l' the number of different tables occupied after L customers have walked in. Then 1 ≦ l' ≦ L and it follows the above description that precisely l' tables are occupied. 2. The nth customer chooses the first unoccupied table with probability α / n−1+α , and an occupied table with probability c / n−1+α, where c is the number of people sitting at that table.

In the above, α is a scalar parameter of the process. One might check that the above does define a probability distribution. Let us denote by kn the number of different tables occupied after n customers have walked in. Then 1 ≦ kn ≦ n and it follows from the above description that precisely tables 1,..., kn are occupied.

 Anmerkungen Eine Quelle ist nicht angegeben. In der Quelle ist der Bruch typografisch korrekt dargestellt. Durch die Darstellung von Rh ist der Formel verfälscht, es musste α/(L — 1 + α) sein. Sichter (Hindemith), WiseWoman

 Bearbeitet: 11. August 2012, 19:33 WiseWomanErstellt: 31. July 2012, 21:46 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 137, Zeilen: 23-25
Quelle: Blei 2007
Seite(n): 1, Zeilen: 13-16
Imagine a restaurant with countable infinitely many tables, labelled 1, 2, .. , L = ∞. Customers walk in and sit down at one table. The tables are chosen according to the following random process. The first customer always chooses the first table and orders a dish. Imagine a restaurant with countably infinitely many tables, labelled 1, 2, ....

Customers walk in and sit down at some table. The tables are chosen according to the following random process.

1. The first customer always chooses the first table.

 Anmerkungen Ein Quellenverweis fehlt. Auf der nächsten Seite, nach einem kurzen Einschub aus einer anderen Quelle, geht die Übernahme aus Blei 2007 weiter: Rh/Fragment 138 02 Sichter (Hindemith), WiseWoman

 Bearbeitet: 11. August 2012, 15:40 HindemithErstellt: 1. August 2012, 19:27 (Graf Isolan)

 Typus BauernOpfer Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 85, Zeilen: 24-26
Quelle: Poon et al. 2003
Seite(n): 942-943, Zeilen: S.942,12-13 - S.943,1
Also they note that tail index estimates are significantly reduced when returns are filtered for heteroskedasticity and that the reduction is the most dramatic when the SV model is used. [Seite 942]

From Table 3 we note that tail index estimates are significantly reduced when stock returns are filtered for heteroskedasticity, and the reduction is the

[Seite 943]

most dramatic when the SV filter is used.

 Anmerkungen keine Kennzeichnung der Übernahme, keine adäquate Quellenangabe. Man beachte auch die vorrausgehende Übernahme aus derselben Quelle: Rh/Fragment 085 21. Dort ist die Quelle genannt, jedoch ohne klarzustellen dass aus ihr wörtlich übernommen wird. Sichter (Graf Isolan), Hindemith

 Bearbeitet: 11. August 2012, 14:50 HindemithErstellt: 31. July 2012, 20:30 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 129, Zeilen: 24-35
Quelle: Smith 2003
Seite(n): 50, Zeilen: 15-18, 22-28
We are interested in the extremal properties of this process. Without loss of generality, we consider the case where all marginal distributions have unit Frèchet [sic!] distribution.

Definition 5.2.1. The process Yij is called max-stable if all finite dimensional distributions are max-stable, i.e., for any n ≥ 1, r ≥ 1

${\scriptstyle \mathbb P}$(Yij ≤ ruij: 1≤i≤n, 1≤j≤d)r = ${\scriptstyle \mathbb P}$(Yij ≤ uij: 1≤i≤n, 1≤j≤d).

Furthermore, a process Xij for i = 1,...,n, j = 1,...,d, is said to be in the domain of attraction of a max-stable process Yij if there exist normalising constants anij > 0, bnij such that for any finite r

${\scriptstyle \lim\limits_{n\to\infty}\mathbb{P}\left(\frac{X_{ij}-b_{nij}}{a_{nij}}\le ru_{ij}:1\le i\le n, 1\le j\le j [sic!] \right)^r}$
${\scriptstyle = \mathbb{P}(Y_{ij}\le u_{ij}: 1\le i\le n, 1\le j\le d). \qquad (5.2.1)}$

Since we assume a priori that the process Xij also has unit Frèchet [sic!], then we may take anij = n, bnij = 0.

If we are interested in the extremal properties of this process, then for the same reasons as with multivariate extremes, it suffices to consider the case where all the marginal distributions have been transformed to unit Fréchet. Such a process is called max-stable if all the finite-dimensional distributions are max-stable, i.e. for any n ≥ 1, r ≥ 1

[...]

Pr(Yid ≤ nyid: 1≤i≤r, 1≤d≤D)n = Pr(Yid ≤ yid: 1≤i≤r, 1≤d≤D). (7.7)

Corresponding to this, a process {Xid : i = 1,2,...; 1≤d≤D} is said to be in the domain of attraction of a max-stable process {Yid : i = 1,2,...; 1≤d≤D} if there exist normalising constants anid > 0, bnid such that for any finite r

${\scriptstyle \lim\limits_{n\to\infty}Pr\left\{\frac{X_{id}-b_{nid}}{a_{nid}}\le ny_{id}:1\le i\le r, 1\le d\le D \right\}^n}$
${\scriptstyle = Pr(Y_{id}\le y_{id}: 1\le i\le r, 1\le d\le D). \qquad (7.8)}$

If we assume a priori that the X process also has unit Fréchet margins, then we may take anid = n, bnid = 0.

 Anmerkungen Keine Kennzeichnung der Übernahme, kein Hinweis auf die Quelle. Obwohl es sich hier im Wesentlichen um eine Definition handelt, so sind doch auch erklärende Bemerkungen wörtlich übernommen worden. Fréchet ist in der Quelle richtig geschrieben; bei der Übernahme ist das Wort "margins" verlorengegangen Sichter (Graf Isolan) Plagiatsfischer

 Bearbeitet: 11. August 2012, 14:41 HindemithErstellt: 1. August 2012, 19:15 (Graf Isolan)

 Typus BauernOpfer Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 85, Zeilen: 21-24
Quelle: Poon et al. 2003
Seite(n): 929, Zeilen: 14-16
Poon et al. (2003) using a range of volatility filters find that tail index and tail dependence can be partially captured by models for heteroscedasticity. Moreover, they find that there is no clear reason to prefer one volatility filter over another. Using a range of volatility filters, we find that tail index and tail dependence can be partially captured by models for heteroskedasticity. We find there is no clear reason to prefer one volatility filter over another.
 Anmerkungen keine Kennzeichnung des übernommenen Wortlauts: wie auch an anderen Stellen zu beobachten wurde die Selbstbeschreibung anderer Autoren identisch übernommen. Sichter (Graf Isolan), Hindemith

 Bearbeitet: 11. August 2012, 14:30 HindemithErstellt: 1. August 2012, 18:31 (Graf Isolan)

 Typus BauernOpfer Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 85, Zeilen: 27-32
Quelle: Davis und Mikosch 2006
Seite(n): 1, 8, Zeilen: 1: 23-27; 8: 28-29
In addition to this Davis and Mikosch (2006b) showed that unlike the situation for GARCH processes (Davis and Mikosch (2006a)), there is no extremal clustering for SV processes in both the light- and heavy-tailed cases. That is, large values of the processes do not come in clusters. More precisely, the large sample behaviour of maxima is the same as that of the maxima of the associated iid sequence. So while both stochastic volatility and GARCH processes exhibit volatility clustering, only the GARCH has clustering of extremes. Interestingly, and unlike the situation for GARCH processes (see Davis and Mikosch [5]), there is no extremal clustering for stochastic volatility processes in both the light- and heavy-tailed cases. That is, large values of the processes do not come in clusters. More precisely, the large sample behavior of Mn is the same as that of the maxima of the associated iid sequence [...]

[Seite 8: 28-29]

So while both stochastic volatility and GARCH processes exhibit volatility clustering, only the GARCH has clustering of extremes.

 Anmerkungen Nichts wurde als Übernahme gekennzeichnet; dass dieser Abschnitt selbst wörtlich aus "Davis and Mikosch (2006b)" stammt, wird überhaupt nicht ersichtlich. Der Verweis auf Davis and Mikosch (2006a) stammt auch aus der Quelle. Sichter (Graf Isolan), Hindemith

 Bearbeitet: 11. August 2012, 14:09 HindemithErstellt: 1. August 2012, 16:48 (Graf Isolan)

 Typus KomplettPlagiat Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 71, Zeilen: 38-39
Quelle: Iwatsubo und Inagaki 2006
Seite(n): 10, Zeilen: 23-24
Japan did not suffer from a crisis, though stock prices in Japan are likely to influence other Asian stock markets and hence are also considered. Unlike Hong Kong and Korea, Japan did not suffer from a crisis, though stock prices in Japan are likely to influence other Asian stock markets and hence are also considered.
 Anmerkungen keinerlei Kennzeichnung als Übernahme, keine Quellenangabe. Auf der nächsten Seite gibt es weitere Übernahmen aus derselben Quelle. Sichter (Graf Isolan), Hindemith

 Bearbeitet: 11. August 2012, 14:01 HindemithErstellt: 1. August 2012, 16:18 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 72, Zeilen: 1-4
Quelle: Iwatsubo und Inagaki 2006
Seite(n): 5, Zeilen: 22-25
[Second, contagion effects defined] as an increment in the functional tail dependence are stronger from the U.S.A market to Asian markets than from Japan, indicating that U.S. market plays a major role in the transmissions of information to foreign markets. Third, the intensity of contagion is significantly greater during the Asian financial crisis than after the crisis. Second, contagion effects are greater from U.S. market to Asian markets than in the reverse direction, indicating that the U.S. market plays a major role in the transmission of information to foreign markets. Third, the intensity of contagion was significantly greater during the Asian financial crisis than after the crisis.
 Anmerkungen Ohne Kennzeichnung werden die Schlussfolgerungen einer anderen Arbeit wortwörtlich übernommen (selbst wenn die dortige Untersuchung sich von der von Rh unterscheidet); die Quelle bleibt ungenannt. Sichter (Graf Isolan), Hindemith

 Bearbeitet: 11. August 2012, 11:05 HindemithErstellt: 1. August 2012, 11:57 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 61, Zeilen: 7-8
Quelle: Hsing et al. 2003
Seite(n): 0, Zeilen: 8-10
Hsing et al. (2004) introduce a new dependence function which allows us to capture the complete extreme dependence structure and to present a nonparametric estimation procedure. We introduce a new dependence function which allows us to capture the complete extreme dependence structure and present a nonparametric estimation procedure.
 Anmerkungen Die (Selbst)Beschreibung aus der Einleitung der Quelle wird ungekennzeichnet identisch übernommen. Sichter (Graf Isolan), Hindemith

 Bearbeitet: 11. August 2012, 09:42 HindemithErstellt: 28. July 2012, 11:11 (Plagiatsfischer)

 Typus Verschleierung Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 215, Zeilen: 13-16
Quelle: Dungey et al. 2008
Seite(n): 1, Zeilen: 17-19
In the second period of the study the empirical results show that financial crises are not too different for these countries as all linkages are statistically important across all crises. However the strength of these linkages does vary across the two crises. […] the empirical results show that financial crises are indeed alike, as all linkages are statistically important across all crises. However, the strength of these linkages does vary across crises.
 Anmerkungen Als Textbaustein verwendet ohne Quellenangabe. Sichter (Plagiatsfischer), Hindemith

 Bearbeitet: 10. August 2012, 09:23 HindemithErstellt: 9. August 2012, 21:37 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 19, Zeilen: 23-28
Quelle: Boldi 2004
Seite(n): 27, Zeilen: 2-7
In the absence of this condition, the dependence structure is such that large value has a greater chance of being followed by another one. If the time between two consecutive such values is small relative to n, the passage to the limit will merge those two extremes onto the same time. Thus, the limit process is then not a Poisson process but a compound Poisson process: any occurrence can be multiple rather than single. The multiplicity is usually random and is called the cluster size distribution π(∙). In the absence of condition D', the dependence structure is such that a large value has a greater chance of being followed by another one. If the time between two consecutive such values is small relative to n, the passage to the limit will merge those two extremes onto the same time. The limit process is then not a Poisson process but a compound Poisson process: any occurrence can be multiple rather than single. The multiplicity is usually random and is called the cluster size distribution.
 Anmerkungen Ein Quellenverweis fehlt Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 9. August 2012, 19:55 HindemithErstellt: 2. August 2012, 07:31 (Plagiatsfischer)

 Typus KomplettPlagiat Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 114, Zeilen: 23-27
Quelle: Roncalli 2001
Seite(n): 4, Zeilen: Spalte 1, 10-14; Spalte 2, 4-6
4.5.3.1. Stress testing. The extreme value theory is now familiar to practitioners. It allows, for example, to apply stress scenarios to a portfolio. However, the extension to the multivariate case is a difficult issue.

To illustrate how this result can be used for risk management, we consider an example which focuses on the extremes of the three bivariate pairs.

3.2 Stress testing

The extreme value theory is now familiar to practitioners. It allows, for example, to apply stress scenarios to a portfolio. However, the extension to the multivariate case is a difficult issue. [...]

To illustrate how this result can be used for risk management, we consider an example which focuses on the extremes of the pair (CAC40, DowJones)

 Anmerkungen Es ist kein Quellenverweis vorhanden. Sichter Hindemith

 Bearbeitet: 9. August 2012, 18:58 HindemithErstellt: 8. August 2012, 14:56 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 98, Zeilen: 1-5
Quelle: Daley VereJones 2003
Seite(n): 249, Zeilen: 25-27, 29-33, 38
[Similarly,] the conditional mark density refers to the distribution to be anticipated at the end of a time interval, not immediately after the next interval has begun.

Other form to write λ*(t,x) is through the H-intensity of the ground process and the conditional density of a mark at t given Ht−

Similarly, the conditional mark density refers to the distribution to be anticipated at the end of a time interval, not immediately after the next interval has begun. [...]

It is often convenient to write

λ*(t,κ) = λ*g(t) f*(κ∣t) , (7.3.3)

where λ*g(t) is the H-intensity of the ground process [...], and f*(κ∣t) is the conditional density of a mark at t given Ht− [...]

 Anmerkungen Eine Quellenangabe fehlt. Die Übernahme beginnt auf der Vorseite: Rh/Fragment 097 10 Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 8. August 2012, 22:20 HindemithErstellt: 27. July 2012, 16:34 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 31, Zeilen: 21-27
Quelle: Smith und Weissman 1996
Seite(n): 2-3, Zeilen: S.2, 29-30 - S.3, 1ff
Just as in one dimension it is the key parameter relating the extreme value properties of a stationary process to those of independent random vectors from the same d-dimensional marginal distribution. However, unlike the one dimensional case, it is not a constant for the whole process, but instead dependences on the vector τ. Some elementary properties include:

(1) $0 \le \theta(\tau) \le 1$ for all τ.

(2) For each $j= 1,\dots d,$ Xij has extremal index $\theta_j = \lim_{i_{i\ne j}\to 0^+} \theta(\tau_1,\dots,\tau_d).$

(3) $\theta(c\tau) = \theta(\tau)$ for all c > 0 (Theorem 1.1 of Nandagopalan (1994))

[Seite 2]

Just as in one dimension, it is the key parameter relating the extreme-value properties of a stationary process to those of independent random

[Seite 3]

vectors from the same D-dimensional marginal distribution. However, unlike the one-dimensional case, it is not a constant for the whole process, but instead depends on the vector τ. Some elementary properties include

(i) $0 \le \theta(\tau) \le 1$ for all τ,

(ii) if τd > 0 but τd' = 0 for all $d' \ne d,$ then $\theta(\tau) = \theta_d,$ the extremal index for the dth component process; namely $\theta(0,\dots, 0,\tau_d,0,\dots, 0) = \theta_d$

(iii) $\theta(c\tau) = \theta(\tau)$ for all c > 0 (Theorem 1.1 of Nandagopalan, 1994)

 Anmerkungen Übernahme nicht gekennzeichnet, Quelle nicht angegeben. Sichter (Graf Isolan) Plagiatsfischer

 Bearbeitet: 8. August 2012, 21:40 HindemithErstellt: 28. July 2012, 12:58 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 15, Zeilen: 11-18
Quelle: Degen 2006
Seite(n): 6, Zeilen: 7-15
Theorem 2.2.6. (Characterization of MDAα(x)))

The distribution function F belongs to the maximum domain of attraction of Ψα(x) (α>0) if and only if xF < ∞ and $\bar{F}(x_F - 1/x)\in \mathcal{R}_{-\alpha}$. In that case

an-1(Mn-xF)$\xrightarrow{d}$ Ψα

with $a_n = x_F - F^\leftarrow(1-1/n)$

Proof. See for instance Resnick (1987), Proposition 1.13, pp. 59. $\square$

Noting that Ψα(-x-1)=Φα(x) for x>0, we are not surprised that MDAα(x)) and MDAα(x)) are closely related.

Noting that Ψα(-x-1)=Φα(x) for x>0, we are not surprised that MDAα(x)) and MDAα(x)) are closely related:

Theorem 1.3 (Characterization of MDAα(x)))

The df F belongs to the maximum domain of attraction of Ψα(x) (α>0) if and only if xF < ∞ and $\bar{F}(x_F - 1/x)\in RV_{-\alpha}$. In that case

an-1(Mn-xF)$\xrightarrow{d}$ Ψα

with $a_n = x_F - F^{\leftarrow} (1-1/n).$

Proof. The proof essentially uses the Fréchet-case. For details see Resnick [34], pp. 59-62. $\square$

 Anmerkungen keine Kennzeichnung als Übernahme, keine Quellenangabe. Das Theorem für sich allein ist durch den Verweis auf Resnick wohl ausreichend belegt. Durch die Übernahme des Kommentars "Noting that ..." ist die Übernahme aus der Quelle aber klar. Sichter (Graf Isolan) Plagiatsfischer, Hindemith

 Bearbeitet: 8. August 2012, 20:41 HindemithErstellt: 23. July 2012, 21:12 (Plagiatsfischer)

 Typus KomplettPlagiat Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 1, Zeilen: 8-13
Quelle: Embrechts 2008
Seite(n): 6, Zeilen: 2-9
In a speech in Dublin, Charlie McCreevy, the European Market Commissioner, denounced

"The irresponsible lending, blind investing, bad liquidity management, excessive stretching of rating agency brands and defective value at risk modelling that prompted the turmoil of recent months" (red. subprime credit crisis). Financial Times, Friday, October 26, 2007.

In a speech in Dublin, Charlie McCreevy, the European Market Commissioner, denounced

"the irresponsible lending, blind investing, bad liquidity management, excessive stretching of rating agency brands and defective value-at-risk modelling that prompted the turmoil of recent months" (red. subprime credit crisis). (Financial Times, Friday, October 26, 2007)

 Anmerkungen Keine Quellenangabe. s. Diskussion. Sichter (KnallErbse), Hindemith

 Bearbeitet: 8. August 2012, 16:28 HindemithErstellt: 26. July 2012, 18:02 (Plagiatsfischer)

 Typus Verschleierung Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 98, Zeilen: 15-18
Quelle: Daley VereJones 2003
Seite(n): 252, Zeilen: 10-14
Notice, that in a process with independent marks, the ground process and the marks are completely independent, whereas for a process with unpredictable marks, the marks can influence the subsequent evolution of the process, though the ground process does not influence the distribution of the marks. In a process with independent marks, the ground process and the marks are completely decoupled (i.e. they are independent processes), whereas for a process with unpredictable marks, the marks can influence the subsequent evolution of the process, though the ground process does not influence the distribution of the marks.
 Anmerkungen Es ist keine Quellenangabe vorhanden. Auch die Proposition 4.3.15, die der Fundstelle vorrausgeht, ist in der Quelle vor der hier dokumentierten Passage zu finden (Proposition 7.3.V). Sichter (Plagiatsfischer), Hindemith

 Bearbeitet: 7. August 2012, 18:39 HindemithErstellt: 31. July 2012, 21:57 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 138, Zeilen: 1-2
Quelle: Hoffman_et_al._2008
Seite(n): 2 (Exzerpt), Zeilen: Spalte 1 24-28
[The first customer always chooses the first table and orders a dish. The second customer enters and decides either to sit at the first table with a probability 1/1 + α] or a new table with probability α /1 + α. When sitting at a new table the customer orders a new dish. This process continues for each new customer. The first customer sits at the first table and orders a dish. The second customer enters and decides either to sit at the first table with probability 1/1 + α or a new table with probability α /1 + α. When sitting at a new table the customer orders a new dish. This process continues for each new customer
 Anmerkungen Ein Quellenverweis fehlt. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 7. August 2012, 17:23 HindemithErstellt: 7. August 2012, 01:37 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 93, Zeilen: 7-12
Quelle: Daley VereJones 2003
Seite(n): 184, Zeilen: 4-7, 21-24
The events immigrants arrive according to a Poisson process at the constant rate μ, while the offspring arise as elements of a finite Poisson process that is associated with some point already constructed.

An important task is to find conditions that ensure the existence of stationary in this process, i.e., of realizations of point sets {ti} on the whole space T = IR having structure above and with distribution invariant under translation.

Immigrants {yj}, say, arrive according to a Poisson process at constant rate μc, while the offspring arise as elements of a finite Poisson process that is associated with some point already constructed. [...]

An important task is to find conditions that ensure the existence of a stationary Hawkes process (i.e. of realizations of point sets {xi} on the whole space X = IRd having the structure above and with distributions invariant under translation).

 Anmerkungen Auf S. 91 findet sich folgender Hinweis auf die Quelle: "The results shown in the next section are based on first volume of Daley and Vere-Jones (2003)." Wörtliche Zitate sind damit aber nicht abgedeckt. Die folgende Proposition 4.3.7. findet sich dann auch sehr ähnlich in der Quelle (Seite 203) Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 7. August 2012, 17:23 HindemithErstellt: 7. August 2012, 00:58 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 90, Zeilen: 38-40
Quelle: Daley VereJones 2003
Seite(n): 157, Zeilen: 20-25
These processes could be already covered formally by the general theory of point processes, as they can be represented as a special type of point process on a product space. However, marked [point processes are worth additional studying because of their wide range of applications and their conceptual importance.] Such processes are already covered formally by the general theory, as they can be represented as a special type of point process on a product space. However, marked point processes are deserving of study in their own right because of their wide range of applications, such as in queueing theory, and their conceptual importance [...]
 Anmerkungen Kein Quellenverweis vorhanden Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 7. August 2012, 17:22 HindemithErstellt: 29. July 2012, 13:35 (WiseWoman)

 Typus Verschleierung Bearbeiter WiseWoman, Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 137, Zeilen: 25-26
Quelle: Hoffman_et_al._2008
Seite(n): 2 (Exzerpt), Zeilen: Spalte 1 24-28
The first customer always chooses the first table and orders a dish. The second customer enters and decides either to sit at the first table with a probability 1/1 + α [or a new table with probability α /1 + α. When sitting at a new table the customer orders a new dish. This process continues for each new customer.] The first customer sits at the first table and orders a dish. The second customer enters and decides either to sit at the first table with probability 1/1 + α or a new table with probability α /1 + α. When sitting at a new table the customer orders a new dish. This process continues for each new customer
 Anmerkungen Ein Quellenverweis fehlt. Sichter (WiseWoman), (Hindemith) Plagiatsfischer

 Bearbeitet: 6. August 2012, 17:56 Graf IsolanErstellt: 28. July 2012, 20:01 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 161, Zeilen: 2-6
Quelle: Alexander Sheedy 2008
Seite(n): 2233, Zeilen: 2. Spalte: 41-47
Traditional stress testing [sic!] are based on historical data or they are hypothetical and can involve large movements, hence the probability of an extreme outcome is unknown and many extreme yet plausible possibilities are ignored. Many stress tests also fail to incorporate the characteristics that markets are known to exhibit in crisis periods, namely, increased probability of further large movements, increased comovement between markets, greater implied volatility and reduced liquidity. However traditional stress tests can be criticised for being conducted outside the context of a risk model, hence the probability of an extreme outcome is unknown and many extreme yet plausible possibilities are ignored. Many stress tests also fail to incorporate the characteristics that markets are known to exhibit in crisis periods, namely, increased probability of further large movements, increased co-movement between markets, greater implied volatility and reduced liquidity.
 Anmerkungen Kein Quellenverweis vorhanden. der erste Halbsatz ist noch unterschiedlich, doch dann ist die Übernahme wörtlich. Sichter (Hindemith), Graf Isolan

 Bearbeitet: 6. August 2012, 16:18 HindemithErstellt: 26. July 2012, 14:41 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 154, Zeilen: 33-38
Quelle: Spiegel - Schultz 2008
Seite(n): 1 (internet version), Zeilen: 5-12
In the case of Germany, the stock market declines are largely attributable to steep losses in the financial industry in the year 2008, as for example, the share price of Commerzbank with losses of 52,9 percent, with Deutsche Bank declining by 26,65 percent, Deutsche Postbank falling by 45,08 percent, Infineon by 25,87 percent and Siemens by 18,17 percent. But more than anything, the skittishness on the stock market in Germany is being caused by the Lehman bankruptcy. The declines on Germany's DAX index are largely attributable to steep losses in the financial industry. The share price of Commerzbank temporarily fell by close to 12 percent, with Deutsche Bank declining by 8.5 percent and Allianz by 7.9 percent.

But more than anything, the skittishness on the stock market in Germany is being caused by the fact that the Lehman bankruptcy threatens to create fresh losses for German banks.

 Anmerkungen der umgebende Fließtext wurde offensichtlich ohne Kennzeichnung dem Spiegel entnommen; woher das Zahlenmaterial stammt, bleibt ungeklärt Sichter (Graf Isolan) Plagiatsfischer

 Bearbeitet: 6. August 2012, 16:18 HindemithErstellt: 27. July 2012, 23:33 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 68, Zeilen: 23-25
Quelle: Worthington et al. 2004
Seite(n): 7, Zeilen: 1-3
Much of the work on Asian financial market interrelationships has been constructed using correlation techniques, only few recent works have taken advantage of the sizeable advances in Copulas [...] Finally, while more recent work has taken advantage of the sizeable advances in cointegration techniques, much of the work on Asian financial market interrelationships has been constructed using simple correlation techniques.
 Anmerkungen Die Übernahme bleibt ungekennzeichnet, die Quelle ist nicht angegeben. Sichter (Graf Isolan) Plagiatsfischer

 Bearbeitet: 6. August 2012, 16:18 HindemithErstellt: 27. July 2012, 23:54 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 109, Zeilen: 32-36
Quelle: Sec news 1998
Seite(n): 1, Zeilen: 9-14
On Monday, October 27, the Dow Jones Industrial Average declined by 554.26 points (7.18%) to close at 7161.15. This represented the tenth largest percentage decline in the index since 1915. October 27 was also the first time that the cross-market trading halt circuit breaker procedures had been used since their adoption in 1988. On Monday, October 27, the Dow Jones Industrial Average declined 554.26 points (7.18%) to close at 7161.15. This represented the tenth largest percentage decline in the index since 1915. October 27 was also the first time that the cross-market trading halt circuit breaker procedures had been used since their adoption in 1988.
 Anmerkungen Ein Quellenverweis fehlt. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 6. August 2012, 16:18 HindemithErstellt: 28. July 2012, 08:31 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 145, Zeilen: 1-8
Quelle: Chen et al. 2006
Seite(n): 4, Zeilen: 22-28
Alternatively, a Bayesian approach can be used to combine the prior distribution for the parameters and the likelihood, resulting in a joint posterior distribution:

[EQUATION, equivalent to equation in the source] (5.5.2)

However, the joint posterior takes a highly complicated form. Thus, it is generally not feasible to perform analytical inference based on the above posterior distribution. The MCMC approaches have typically been used to calculate the joint posterior and, of the approaches that have been proposed in the literature, Gibbs sampling is suitable for mixture models.

Alternatively, a Bayesian approach can be used to combine the prior distribution for the parameters and the likelihood, resulting in a joint posterior distribution:

[EQUATION] (3)

However the joint posterior takes a highly complicated form. Thus it is generally not feasible to perform any analytical inference based on the above posterior distribution. MCMC approaches have typically been used to calculate the joint posterior and of the approaches proposed in the literature, Gibbs sampling is suitable for mixture models

 Anmerkungen Keine Quellenangabe vorhanden. Die oben nicht dokumentierte Gleichung ist in der Dissertation equivalent zur Gleichung in der Quelle. Variablen und Verteilungen haben nur andere Namen. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 6. August 2012, 16:18 HindemithErstellt: 28. July 2012, 10:05 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 144, Zeilen: 33-35
Quelle: Chen et al. 2006
Seite(n): 4, Zeilen: 17-21
Given the set y the classical approach to estimate the parameters (μl, Ωl), is to maximize the likelihood by using the EM algorithm (Dempster et al. (1977)). The EM algorithm guarantees convergence to a local maximum, with the quality of the maximum being heavily [dependent on the random initialization of the algorithm.] Given a set of training data with N observations, x={x1,...,xN}, the classical approach to estimating the Gaussian mixture model parameters, (μ,τ,π), is to maximize the likelihood using the expectation-maximization (EM) algorithm (Dempster et al., 1977). The EM algorithm guarantees convergence to a local maximum, with the quality of the maximum being heavily dependant [sic] on the random initialization of the algorithm.
 Anmerkungen Eine Quellenangabe fehlt. Die Übernahme setzt sich auf der nächsten Seite fort: Rh/Fragment_145_01 Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 6. August 2012, 16:17 HindemithErstellt: 28. July 2012, 14:23 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 87, Zeilen: 1-2
Quelle: Gencay et al 2002
Seite(n): 2, Zeilen: 12-14
[Instead of forcing a single distribution for the entire sample, it is] possible to investigate only the tails of the sample distribution using the models proposed, if only the tails are important for practical purposes. Instead of forcing a single distribution for the entire sample, it is possible to investigate only the tails of the sample distribution using limit laws, if only the tails are important for practical purposes.
 Anmerkungen Keine Quelle angegeben Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 6. August 2012, 16:16 HindemithErstellt: 28. July 2012, 17:56 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 24, Zeilen: 19-21
Quelle: Wüthrich 2004
Seite(n): 3, Zeilen: 10-12
The idea behind the concept of copulas is to separate a multivariate distribution function into two parts, one describing the dependence structure and the other describing marginal behaviour, respectively. The idea behind the concept of copulas is to separate a multivariate distribution function into two parts, one describing the dependence structure and the other one describing marginal behaviours, respectively.
 Anmerkungen Kurz und auch keine sehr neuartige Einsicht, aber doch eindeutig wörtlich übernommen. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 5. August 2012, 10:54 HindemithErstellt: 29. July 2012, 13:39 (Graf Isolan)

 Typus KomplettPlagiat Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 140, Zeilen: 1-3
Quelle: Teh 2007
Seite(n): 2, Zeilen: 21-26
[In the case of the DP, it is a distribution over probability measures, which are functions with certain special properties which allow them to be interpreted] as distributions over some probability space. Thus, draws from a DP can be interpreted as random distributions. For a distribution over probability measures to be a DP, its marginal distributions have to take on a specific form which we shall give below. In the case of the DP, it is a distribution over probability measures, which are functions with certain special properties which allow them to be interpreted as distributions over some probability space Θ. Thus draws from a DP can be interpreted as random distributions. For a distribution over probability measures to be a DP, its marginal distributions have to take on a specific form which we shall give below.
 Anmerkungen kein Hinweis auf eine Übernahme, keine Quellenangabe. Die Übernahme beginnt schon auf der Vorseite: Rh/Fragment_139_15 Sichter (Graf Isolan), Hindemith

 Bearbeitet: 5. August 2012, 10:53 HindemithErstellt: 29. July 2012, 13:25 (Graf Isolan)

 Typus KomplettPlagiat Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 139, Zeilen: 15-19
Quelle: Teh 2007
Seite(n): 2, Zeilen: 18-23
Formally, the DP is a stochastic process whose sample paths are probability measures with probability one. Stochastic processes are distributions over function spaces, with sample paths being random functions drawn from the distribution. In the case of the DP, it is a distribution over probability measures, which are functions with certain special properties which allow them to be interpreted [as distributions over some probability space.] Formally, the Dirichlet process (DP) is a stochastic process whose sample paths are probability measures with probability one. Stochastic processes are distributions over function spaces, with sample paths being random functions drawn from the distribution. In the case of the DP, it is a distribution over probability measures, which are functions with certain special properties which allow them to be interpreted as distributions over some probability space Θ.
 Anmerkungen kein Hinweis auf eine Übernahme, keine Quellenangabe. Die Übernahme wird hier fortgesetzt: Rh/Fragment_140_01 Sichter (Graf Isolan), Hindemith

 Bearbeitet: 5. August 2012, 10:48 HindemithErstellt: 29. July 2012, 14:03 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 138, Zeilen: 17-21
Quelle: Teh 2007
Seite(n): 7, Zeilen: 32-37
This slow growth of the number of clusters makes sense because of the rich-gets-richer phenomenon: we expect there to be large clusters thus the number of clusters l' to be far smaller than the number of observations L. Notice that α controls the number of clusters in a direct manner, with larger implying a larger number of clusters a priori. This intuition will help in the application of DPs to mixture models. This slow growth of the number of clusters makes sense because of the rich-gets-richer phenomenon: we expect there to be large clusters thus the number of clusters m to be far smaller than the number of observations n. Notice that α controls the number of clusters in a direct manner, with larger α implying a larger number of clusters a priori. This intuition will help in the application of DPs to mixture models.
 Anmerkungen keine Kennzeichnung der Übernahme; kein Quellenverweis. Man beachte das ausgelassene α in der Dissertation. Sichter (Graf Isolan), Hindemith

 Bearbeitet: 3. August 2012, 13:54 WiseWomanErstellt: 2. August 2012, 21:04 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 127, Zeilen: 27-31
Quelle: Zhang Smith 2004b
Seite(n): 1, Zeilen: 9-14
The infinite dimensional generalization of extreme value theory, which leads to max-stable processes, introduced by De Haan (1984). These processes have the potential to describe clustering behaviour. One of the most important features of max-stable processes is that they do not only model the dependence among the marginals, but also model the dependence across time. Max-stable processes, introduced by de Haan (1984), are an infinite-dimensional generalization of extreme value theory which does have the potential to describe clustering behavior. [...] One of the most important features of max-stable processes is that it does not only model the cross-sectional dependence, but also models the dependence across time.
 Anmerkungen Inhaltlich und in vielen Formulierungen aus der Quelle übernommen, ohne dass diese genannt wäre. Sichter (Hindemith), Plagiatsfischer

 Bearbeitet: 3. August 2012, 13:53 WiseWomanErstellt: 1. August 2012, 22:29 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 130, Zeilen: 11-16
Quelle: Zhang Smith 2004b
Seite(n): 2, Zeilen: 15-23
Smith and Weissman (1996) characterized the conditions under which the multivariate extremal index from a stationary time series could be calculated from a max-stable process with the same limiting distributions for any finite dimensional multivariate extremes. Furthermore, they show that any max-stable process in d-dimensions could be approximated with arbitrary accuracy by one of M4 form through a direct generalisation of the result of Deheuvels (1983) for one dimensional case. The main result of Smith and Weissman (1996) was to characterize the conditions under which the multivariate extremal index – introduced by Nandagopalan (1990) – for a general stationary process could be approximated by one from an M4 process. First, they proved that under suitable mixing conditions, the multivariate extremal index from a stationary time series could be calculated from that of a maxstable process with the same limiting distributions for any finite-dimensional multivariate extremes. Second, they argued that any max-stable process in D dimensions could be approximated with arbitrary accuracy by one of M4 form. The latter result is a direct generalization to multivariate processes of a result due to Deheuvels (1983), whose own representation is the D = 1 case of (2.1).
 Anmerkungen Der Sinn und einige Formulierungen finden sich auch in der hier nicht angegebenen Quelle. Es ist auffallend dass auch die Herleitung vor diesem Textfragment eine Entsprechung in der Quelle hat: Dissertation, Quelle Sichter (Hindemith), Plagiatsfischer

 Bearbeitet: 1. August 2012, 21:59 FretErstellt: 1. August 2012, 20:08 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 214, Zeilen: 6-11
Quelle: Poon et al. 2003
Seite(n): 943, Zeilen: 31-37
A first interpretation of this result implies that there is significant dependence between large values of the paired series but that the largest values do not occur concurrently. Since most of the pairs have some degree of asymptotically independent, multivariate extreme value models that assume asymptotic dependence among the different market returns are likely to overestimate the joint risk.

In Figure 6.5.5 we assess how important [...]

From the interpretation of \bar{χ} in Section 2.2, this implies that there is significant dependence between large values of the paired series but that the very largest values do not occur concurrently. Since most of the pairs are asymptotically independent, multivariate extreme value models that assume asymptotic dependency among stock market returns are likely to have overestimated portfolio joint risk. In Section 4 we assess how important [...]
 Anmerkungen kein Hinweis auf eine Übernahme; keine Quellenangabe. Die Vorlage dient hier als reiner Textbaustein. Sichter (Graf Isolan) Plagiatsfischer

 Bearbeitet: 1. August 2012, 19:36 Graf IsolanErstellt: 28. July 2012, 15:20 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 174, Zeilen: 22-28
Quelle: Poon et al. 2003
Seite(n): 931, Zeilen: 1-7
The conventional multivariate extreme value theory has emphasized the asymptotically dependent class resulting in its wide use in all the finance applications. However, if the series are truly asymptotically independent, such an approach will result in the over estimation of extreme value dependence and consequently of the measure of extreme risk.

In particular, this degree of asymptotic independence is directly related to the over estimation of different measures of risk. Despite this potential drawback, the case of asymptotically independent models has so far been missing from the finance literature.

Conventional multivariate extreme value theory has emphasized the asymptotically dependent class resulting in its wide use in all the finance applications listed above. If the series are truly asymptotically independent, such an approach will result in the over-estimation of extreme value dependence, and consequently of the financial risk. The degree of this over-estimation depends on the degree of asymptotic independence. Despite this potential for bias, the case for asymptotically independent models has so far been missing from the finance literature.
 Anmerkungen Keine Quellenangabe vorhanden. Sichter (Hindemith), Graf Isolan

 Bearbeitet: 1. August 2012, 18:12 HindemithErstellt: 31. July 2012, 19:24 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 160, Zeilen: 15-19, 20-23
Quelle: Smith 2003
Seite(n): 58, Zeilen: 13-15, 16-19
We simulate a sample of size 20.000 to test if the fitted M4 process is a realistic representation of the Frèchet-transformed time series and if it can be utilized in common measures in risk management. In a first look at the quality of the simulated data, we displayed a scatterplot among the sample paths simulated from the fitted process and observed if this sample looks similar to those from the original series. [...] One point to note here is that the data was generated so that the marginal distributions were exactly unit Frèchet. In order to provide a fair comparison with the original estimation procedure, the axes were rescaled so that a considerable number of points were present. One test of whether the fitted M4 process is a realistic representation of the Fréchet-transformed time series is whether the sample paths simulated from the fitted process look similar to those from the original series. [...] One point to note here is that although the data were generated so that the marginal distributions were exactly unit Fréchet, in order to provide a fair comparison with the original estimation procedure, the marginal distributions were re-estimated, and transformed according to the estimated parameters, before drawing the scatterplots in Fig. 43 and 44.
 Anmerkungen Keine Kennzeichnung der übernommenen Passagen; keine Quellenangabe. Im Rahmen der Anwendung der von Smith beschriebenen Methodik wurde Originaltext uebernommen. Fréchet ist in der Quelle richtig geschrieben. Sichter (Graf Isolan, KnallErbse) Plagiatsfischer

 Bearbeitet: 1. August 2012, 18:12 HindemithErstellt: 28. July 2012, 23:16 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 3, Zeilen: 24-25
Quelle: Segers 2006
Seite(n): 463, Zeilen: 27-29
The extremal index quantifies the strength of dependence between threshold exceedances X > u, with θ = 1 corresponding to [asymptotic independence and θ ↓ 0 to an increasing propensity of large observations to occur in clusters.] The extremal index θ quantifies the strength of dependence between threshold exceedances {Xi > un}, with θ = 1 corresponding to asymptotic independence and θ ↓ 0 to an increasing propensity of large observations to occur in clusters.
 Anmerkungen Fast wörtliche Übernahme. Ein Verweis auf diese Quelle gibt es nicht. Allerdings wird weiter unten, am Ende des Abschnitts gesagt: "(see for instance Laurini and Tawn (2003); Ferro and Segers (2003))". Bei Ferro and Segers (2003) findet sich diese Stelle so nicht. Sichter (Hindemith) Plagiatsfischer

 Bearbeitet: 1. August 2012, 16:33 WiseWomanErstellt: 27. July 2012, 23:17 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 68, Zeilen: 7-10
Quelle: Worthington et al. 2004
Seite(n): 3, Zeilen: 20-22, 27-28
During the last decade the Asian equity markets have increasingly attracted non Asian investors, particularly from the U.S., with the aim to enjoy the benefit of diversification. However, extreme events as the Asian crisis suggest that the Asian capital markets have become increasingly integrated. [...] Asian equity markets have increasingly attracted non-Asian investors – particularly from the U.S. – to the potential benefits of international diversification. However [...] innovations such as the October 1987 stock market crash and the more recent Asian crises, these factors suggest that Asian capital markets have become increasingly integrated.
 Anmerkungen Übernahme ohne Kennzeichnung und Quellenangabe. Sichter (Graf Isolan), WiseWoman

 Bearbeitet: 1. August 2012, 16:30 WiseWomanErstellt: 27. July 2012, 22:18 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan, Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 72, Zeilen: 5-12
Quelle: Worthington et al. 2004
Seite(n): 12, 13, Zeilen: 12: 20-23, 26-29; 13: 7-8
All of these results appear sensible in terms of the relative importance of these markets in the Asian region. One of the most interesting findings concerns the change in the most influential markets, as measured by the functional tail dependence, in the post-crisis period compared to the pre-crisis period. Once again, this is largely consistent with the notion of "contagion effects" following the onset of the Asian crises and the greater degree of market interdependence in the post-crisis regional economy. Overall, these findings are comparable to most other works in this area. The results obtained in this chapter complement this work in quantifying the interdependencies among Asian equity markets. All of these results appear sensible in terms of the relative importance of these markets in the Asian region. One of the most interesting findings concerns the change in the most influential markets, as measured by causal links, in the post-crisis period as compared to the pre-crisis period. [...] Once again, this is largely consistent with the notion of ‘contagion effects’ following the onset of the Asian crises and the greater degree of market interdependence in the post-crisis regional economy.

Overall, these findings are comparable to most other work in this area. [...]

[...] The results obtained in this paper complement this work in quantifying the interdependencies among Asian equity markets.

 Anmerkungen Keine Kennzeichnung der Übernahme, keine Angabe der Quelle. Man beachte die Ersetzung: "The results obtained in this paper" in der Quelle wird zu "The results obtained in this chapter" in der untersuchten Dissertation. Sichter (Graf Isolan), WiseWoman

 Bearbeitet: 1. August 2012, 16:28 WiseWomanErstellt: 27. July 2012, 21:41 (Graf Isolan)

 Typus KomplettPlagiat Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 73, Zeilen: 1-2
Quelle: Worthington et al. 2004
Seite(n): 13, Zeilen: 28-31
[One of the most interesting findings concerns the change in the most influential markets, as measured by the functional tail dependence, in the] post-crisis period as compared to the pre-crisis period. This is at least one indication of an increasingly interdependent Asian regional market. One of the most interesting findings concerns the change in the most influential markets, as measured by causal links, in the post-crisis period as compared to the pre-crisis period. This is at least one indication of an increasingly interdependent Asian regional market.
 Anmerkungen Abschluss der in Rh/Fragment_072_28 begonnenen Übernahme. Sichter (Graf Isolan), WiseWoman

 Bearbeitet: 1. August 2012, 16:25 WiseWomanErstellt: 27. July 2012, 21:04 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 72, Zeilen: 28-30, 33-42
Quelle: Worthington et al. 2004
Seite(n): 13, Zeilen: 16-19, 20-30
Possible reasons include long-standing trends in trade and investment interaction, the more recent convergence in monetary policies and the almost universal process of microeconomic reform flowing from the crises themselves. [...] This suggests that at least some markets have become more isolated following these macroeconomic shocks. The findings obtained in this chapter have obvious implications, amongst other things, for the purported benefits of international portfolio diversification among the several Asian equity markets. As a result, the strong linkages among the national markets would indicate that the returns from such a strategy have diminished markedly. However, the results also suggest that opportunities for diversification may still exist, especially in some of the smaller markets. In the pre-crisis period most Asian equity markets were relatively isolated from each other or were subject to only a few direct extreme events. One of the most interesting findings concerns the change in the most influential markets, as measured by the functional tail dependence, in the [post-crisis period as compared to the pre-crisis period.] Possible reasons include long-standing trends in trade and investment interaction, the more recent convergence in monetary policies and the almost universal process of microeconomic reform flowing from the crises themselves. [...] This suggests that at least some markets have become more isolated following these macroeconomic shocks.

The findings obtained in this paper have obvious implications, amongst other things, for the purported benefits of international portfolio diversification among the several Asian equity markets. In effect, the strong linkages among the national markets would indicate that the returns from such a strategy have diminished markedly. However, the results also suggest that opportunities for diversification may still exist, especially in some of the smaller markets. In the pre-crisis period most Asian equity markets were relatively isolated from each other or were subject to only a few direct causal links. One of the most interesting findings concerns the change in the most influential markets, as measured by causal links, in the post-crisis period as compared to the pre-crisis period.

 Anmerkungen Keine Kennzeichnung als Zitat, trotz fast vollständiger Übereinstimmung, keine Quellenangabe. Die Passage dient Rh als wesentlicher abschließender Bestandteil seiner "Conclusions" zu den Ergebnissen des Kapitels 3 seiner Dissertation. Umgekehrt stellen sie die "Conclusions" der Quelle dar. Sichter (Graf Isolan), WiseWoman

 Bearbeitet: 1. August 2012, 16:25 Graf IsolanErstellt: 27. July 2012, 09:31 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 207, Zeilen: 19-25
Quelle: Financial Times - Oakley 2008
Seite(n): 1 (internetversion), Zeilen: 2, 4-11, 22-25
In the cases of Russia and Brazil in the recent crisis, their stocks were close to record peaks, its foreign reserves were the envy of the world and some analysts were even describing it as a heaven for investments. Today, largely due to the bursting of the commodity bubble that had underpinned many emerging market economies around the world, the equity market in Russia has fallen a dramatic 70 per cent since May 2008 amid the sharp sell-off in commodity related stocks, while for many of the Latin American countries, such as Brazil, the stock market has dropped 56 per cent this year. Gloom hits Russia and Brazil

By David Oakley

Only five months ago, Russia was riding high. Its stocks were close to record peaks, its foreign reserves were the envy of the world and some analysts were even describing it as a haven for investments.

Today, largely due to the bursting of the commodity bubble that had underpinned many emerging market economies around the world, that glowing outlook has turned decidedly gloomy.

Russia's most-liquid equity market, the Micex, has fallen a dramatic 70 per cent since May amid the sharp sell-off in commodity related stocks.

[...]

For many of the Latin American countries, such as Brazil and Mexico, the national currencies have come under pressure as well as stocks, as plummeting food and oil prices hit exports. The Brazilian stock market has dropped 56 per cent this year, while Mexican equities have fallen more than 40 per cent.

[Copyright The Financial Times Limited 2012.]

 Anmerkungen No mention of the original source is made; citations are not marked as such. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 1. August 2012, 16:24 Graf IsolanErstellt: 27. July 2012, 08:47 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 190, Zeilen: 17-20
Quelle: Corsetti et al. 2005
Seite(n): 5, Zeilen: 5-9
However, interpreting any increase in cross-country covariances and/or correlations as evidence of contagion, may be misleading.

This point can be illustrated by means of a simple example drawing on Forbes (2002). Suppose that the rates of return of the stock market in two countries are linearly related [...]

However, interpreting any increase in cross-country covariances and/or correlations as evidence of contagion may be misleading. We can illustrate this point by means of a simple example drawing on Forbes and Rigobon (2002). Suppose that in normal or “tranquil” times the rates of return of the stock market in two countries are linearly related:
 Anmerkungen Ein Quellenverweis fehlt hier. Die Quelle wird zwei Zeilen zuvor zusammen mit anderen Quellen als "major empirical paper" zitiert. Man beachte dass sich dieses Fragment im Text der Quelle nahtlos an Rh/Fragment_190_07 anschließt. Sichter (Hindemith), KnallErbse

 Bearbeitet: 1. August 2012, 16:23 Graf IsolanErstellt: 27. July 2012, 08:36 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 190, Zeilen: 7-10
Quelle: Corsetti et al. 2005
Seite(n): 5, Zeilen: 2-5
The apparent increase in comovements of asset prices across markets during periods of financial turmoil has lead analysts and market observators to raise the hypothesis of “contagion” in the international transmission of currency and financial crises. The apparent increase in comovements of asset prices across markets during periods of financial turmoil has lead analysts and market commentators to raise the hypothesis of ‘contagion’ in the international transmission of currency and financial crises.
 Anmerkungen Die Quelle ist nicht genannt, wird aber im folgenden Absatz zusammen mit anderen Quellen als "major empirical paper" zitiert. Man beachte, dass aus "commentators" "observators" wird. Der Autor meine vermutlich "observers". Sprachliche Fehler finden sich auch an anderen Stellen der Dissertation, bei denen mit kleinen Auslassungen oder Austauschungen vorgegangen wird. Sichter (Hindemith), KnallErbse

 Bearbeitet: 1. August 2012, 16:21 Graf IsolanErstellt: 1. August 2012, 15:58 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 64, Zeilen: 5-7
Quelle: Hartmann et al. 2004
Seite(n): 12, Zeilen: 15-18
This linkage measure has the advantages that it can be easily extended beyond the bivariate setting. Moreover, one does not need to condition on a specific marginal, whereby one would look only into one direction in the plane of extreme events. The conditional expectation measure E{κ|κ≥ 1} has also the advantages that it can be easily extended beyond the bivariate setting and that one does not need to specify the crashing, conditioning asset whereby one would look only into one direction in the plane.
 Anmerkungen Formulierung in leicht verändertem Kontext ohne Kennzeichnung wortwörtlich übernommen; Quelle wird nicht genannt. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 1. August 2012, 16:19 Graf IsolanErstellt: 27. July 2012, 16:07 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 207, Zeilen: 39-41
Quelle: Hartmann et al. 2004
Seite(n): 11, Zeilen: 21-23
Therefore we would be well advised to turn to a measure which is not conditioned on a particular multivariate distribution and which directly reflects the probabilities and associated crisis levels. Therefore we like to turn to a measure which is not conditioned on a particular multivariate distribution and which directly reflects the probabilities and associated crash levels.
 Anmerkungen keine Kennzeichnung der Übernahme, keine Nennung der Quelle Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 1. August 2012, 10:23 WiseWomanErstellt: 26. July 2012, 15:38 (Graf Isolan)

 Typus KomplettPlagiat Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 154, Zeilen: 25-27
Quelle: Häring und Storbeck 2009
Seite(n): 129, Zeilen: 16-17
The name of the crisis stems from a special segment of the U.S. mortgage market, the market for subprime loans. The name of the crisis stems from a special segment of the U.S. mortgage market — the market for subprime loans.
 Anmerkungen ungekennzeichnete Übernahme Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 1. August 2012, 00:11 Graf IsolanErstellt: 27. July 2012, 14:33 (KnallErbse)

 Typus Verschleierung Bearbeiter KnallErbse Gesichtet
Untersuchte Arbeit:
Seite: 8, Zeilen: 32-37
Quelle: Zhang_2008
Seite(n): 1, Zeilen: 28-32
This chapter addresses the dimensionality issue based on a wider context of extreme value theory; the infinite dimensional generalization of extreme value theory, which leads to max-stable processes, introduced by De Haan (1984). These processes have the potential to describe clustering behaviour. One of the most important features of max-stable processes is that they do not only model the dependence among the marginals, but also model the dependence across time. An infinite-dimensional generalization of extreme value theory leads to max-stable processes, introduced by de Haan (1984), which do have the potential to describe clustering behavior. One of the most important features of max-stable processes is that they not only model the spatial dependence, but also model the dependence across time.
 Anmerkungen Leicht angepasst. Quelle wird hier nicht zitiert. Siehe auch Zhang Smith 2004, Seite 1 unten. Sichter (Knallerbse) Plagiatsfischer

 Bearbeitet: 1. August 2012, 00:08 Graf IsolanErstellt: 27. July 2012, 13:49 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 20, Zeilen: 8-10
Quelle: Embrechts et al. 1997
Seite(n): 16, Zeilen: 4-6
Point processes techniques are by now an unavoidable tool in modern extreme value theory and its results give a deep insight into the structure and occurrence of extreme. Point process techniques are by now an unavoidable tool in modern extreme value theory, and the results are convincing and give a deep insight into the structure and occurrence of extremes.
 Anmerkungen keine Kennzeichnung als Zitat; keine Quellenangabe. Auf die Quelle wird weiter unten tatsächlich noch verwiesen, dort ist sie allerdings nur als weitere Referenz für eine "concise introduction" angegeben. Sichter (Graf Isolan) Plagiatsfischer

 Bearbeitet: 31. July 2012, 20:59 WiseWomanErstellt: 27. July 2012, 16:26 (Plagiatsfischer)

 Typus Verschleierung Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 92, Zeilen: 5-25
Quelle: Daley VereJones 2003
Seite(n): 195;202, Zeilen: 1-13,24-25,35-38;13-17
There exists a rich class of MPPs with a great variety of forms that can be taken by the marks and the variety of dependence relations among marks and locations. Two important classes are defined below

[...]

The next definition characterizes two important types of independence relating to the mark structure of MPPs.

[...]

Of course the most common case of an MPP with independent marks occurs when the marks are iid. Similarly, the most common case of a process with unpredictable marks occurs when the marks are conditionally iid given the past of the process. The most interesting extensions appear when we drop the assumption of completely independent marks and consider ways in which either the marks can influence the future development of the process or the current state of the process can influence the distribution of marks, or both.

The class of MPPs is a great deal richer than might at ﬁrst appear. This is due to the great variety of forms that can be taken by the marks and the variety of

dependence relations that can exist between the marks themselves and their locations. [...] we deﬁne for MPPs the following two classes of point processes.

[...]

The next pair of deﬁnitions characterize two important types of independence relating to the mark structure of MPPs.

[...]

The most common case of an MPP with independent marks occurs when the kappa_i are in fact i.i.d. Similarly, the most common case of a process with unpredictable marks occurs when the marks are conditionally i.i.d. given the past of the process [...]

The most interesting extensions appear when we drop the assumption of completely independent marks and consider ways in which either the marks can influence the future development of the process or the current state of the process can influence the distribution of marks, or both.

 Anmerkungen Die beiden Auslassungen in der Arbeit sind mathematische Definitionen, die eo ipso als mögliches Plagiat ausscheiden. Auf S. 91 findet sich folgender Hinweis auf die Quelle: "The results shown in the next section are based on first volume of Daley and Vere-Jones (2003)." Siehe Diskussion. Sichter KnallErbse

 Bearbeitet: 31. July 2012, 20:58 WiseWomanErstellt: 26. July 2012, 21:00 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 207, Zeilen: 9-18
Quelle: AFP 2008 - US subprime crisis
Seite(n): 1, Zeilen: 4-12, 18-22
On the other hand, the meltdown in the US subprime real-estate market has led until now to a global loss of more 7.7 trillion dollars in stock market value since October 2007. The crisis, which has spread beyond US shores to banks and other sectors worldwide, is one of the most vicious in financial history. The losses are worse than any in the past few decades, including Wall Street's Black Monday of 1987, the 1999 Brazilian real currency crisis and the collapse of hedge fund Long Term Capital Management (LTCM) in 1998. The losses are also greater than those suffered after the September 11, 2001, terror attacks, the Asian financial crisis starting in 1997, Argentina's default on its debt in 2001 and the 1994 Mexican peso crisis. It will take months or even years before Wall Street gets a handle on true cost of the US subprime meltdown and the attendant global credit crunch. NEW YORK (AFP) — The meltdown in the US subprime real-estate market has led to a global loss of 7.7 trillion dollars in stock-market value since October, a report by Bank of America showed Thursday.

The crisis, which has spread beyond US shores to banks and other sectors worldwide, is "one of the most vicious in financial history," according to Bank of America chief market strategist Joseph Quinlan.

Quinlan said in the report that the losses are worse than any in the past few decades, including Wall Street's Black Monday of 1987, the 1999 Brazilian real currency crisis and the collapse of hedge fund Long Term Capital Management (LTCM) in 1998.

[...]

The losses were also greater than those suffered after the September 11, 2001, terro [sic!] attacks, the Asian financial crisis starting in 1997, Argentina's default on its debt in 2001 and the 1994 Mexican peso crisis.

"It could take months or even years before Wall Street and others get a handle on the true cost of the US subprime meltdown and the attendant global credit crunch," Quinlan said.

 Anmerkungen Ohne Kennzeichnung werden hier die Formulierungen eines AFP-Artikels weitgehend wortwörtlich übernommen und dabei auch die Aussagen, die ursprünglich von Quinlan stammen, "verarbeitet". Eine Quellenangabe unterbleibt. Man beachte auch die sprachlichen Fehler, die bei der Verschleierung durch Wortauslassungen im ersten und letzten Satz enstanden sind. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 31. July 2012, 20:09 Graf IsolanErstellt: 26. July 2012, 13:11 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 207, Zeilen: 28-31
Quelle: Gonzalez-Hermosillo 2008
Seite(n): 225, Zeilen: 20-23
Of course, the identification of shocks triggering a crisis is just one dimension to understand financial crises. A second and arguably more important dimension, is to identify the transmission mechanisms that propagate shocks from the source country across national borders and across financial markets. The identification of shocks triggering a crisis is just one dimension to understanding financial crises. A second, and arguably more important dimension, is to identify the transmission mechanisms that propagate shocks from the source country across national borders and across financial markets.
 Anmerkungen Eine Quellenangabe fehlt. Sichter (Hindemith), KnallErbse

 Bearbeitet: 31. July 2012, 19:52 Graf IsolanErstellt: 26. July 2012, 12:11 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 154, Zeilen: 23-25, 28-32
Quelle: Letondu 2008
Seite(n): 26, Zeilen: 2-3, 6-10
In the case of Germany, the collapse of Lehman Brothers on September 15, 2008, marked the climax of the financial crisis and the beginning of the economic recession, as it was announced on November 13, 2008, by Germany's Federal Statistical Office. [...] Germany's banks, already heavily exposed to subprime securities, have been particularly affected by the acute, ongoing tension in the money markets and the financial markets, which have been devastated by a massive flight to quality. Germany's highly export dependent economy is losing steam following a dramatic slowdown in its overseas markets. Germany’s highly export-dependent economy is losing steam following a dramatic slowdown in its overseas markets. [...]

The collapse of Lehman Brothers on September 15 marked the climax of the financial crisis. Germany’s banks, already heavily exposed to subprime securities, have been particularly affected by the acute, ongoing tension in the money markets (3-month OIS-Euribor spreads have scarcely dipped below their historic peak of early October) and the financial markets, which have been devastated by a massive flight to quality.

 Anmerkungen Kein Hinweis auf die Quelle; keine Kennzeichnung übernommener Passagen. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 31. July 2012, 19:48 Graf IsolanErstellt: 26. July 2012, 04:26 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 149, Zeilen: 1-16
Quelle: Neal 2000
Seite(n): 261, Zeilen: 3ff
[In this case we will introduce m temporary auxiliary variables that represent] possible values for the parameters of components that are not associated with any other observations. We then update cl by Gibbs sampling with respect to the distribution that includes these auxiliary parameters.

Because of the fact that the observations yl are exchangeable, and the component labels cl are arbitrary, we can assume that we are updating ci for the last observation, and that the cj for other observations have values in the set {1,...,k-}, We can now visualize the conditional prior distribution for cl given the other cj in terms of these m auxiliary components and their associated parameters. The probability of cl being equal to a c in {1,... ,k-} will be n-l,c / (L — 1 + a), where n-l,c is the number of times c occurs among the cj for j ǂ l. The probability of cl having some other value will be a / (L — 1 + a) which we will split equally among the m auxiliary components we have introduced.

The first step in using this representation to update cl is to sample from the conditional distribution of these auxiliary parameters given the current value of cl and the rest of the state. In the case of the conditional probability (5.5.9) ( i.e., n-l,c > 0) the auxiliary parameters have no connection with the rest of the state or the observations, and are simply drawn independently from G0.

[...], we will introduce temporary auxiliary variables that represent possible values for the parameters of components that are not associated with any other observations. We then update ci by Gibbs sampling with respect to the distribution that includes these auxiliary parameters.

Since the observations yi are exchangeable, and the component labels ci are arbitrary, we can assume that we are updating ci for the last observation, and that the cj for other observations have values in the set {1,...,k-}, [...] We can now visualize the conditional prior distribution for ci given the other cj in terms of m auxiliary components and their associated parameters. The probability of ci being equal to a c in {1,...,k-} will be n-i,c / (n — 1 + a), where n-i,c is the number of times c occurs among the cj for j ǂ i. The probability of ci having some other value will be a / ( n - l + a ) , which we will split equally among the m auxiliary components we have introduced. [...]

[...] The first step in using this representation to update ci is to sample from the conditional distribution of these auxiliary parameters given the current value of ci and the rest of the state. If ci =cj for some j ǂ i, the auxiliary parameters have no connection with the rest of the state, or the observations, and are simply drawn independently from G0

 Anmerkungen Auf der Vorseite wird die Quelle wie folgt erwähnt: "To approximate this integral we use the algorithm 8 by Neal (2000)". Nicht erwähnt wird, dass der erklärende Text auch wörtlich aus der Quelle stammt Sichter (Hindemith), KnallErbse

 Bearbeitet: 31. July 2012, 19:43 Graf IsolanErstellt: 26. July 2012, 04:01 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 144, Zeilen: 16-22
Quelle: Neal 2000
Seite(n): 249, Zeilen: 25-31
The use of DPM models has become computationally feasible with the development of Markov chain methods for sampling from the posterior distribution of the parameters of the component distributions and of the associations of mixture components with observations. Methods based on Gibbs sampling can easily be implemented for models based on conjugate prior distributions, but when nonconjugate priors are used, as is appropriate in many contexts, straightforward Gibbs sampling requires that an often difficult numerical integration be performed. Use of Dirichlet process mixture models has become computationally feasible with the development of Markov chain methods for sampling from the posterior distribution of the parameters of the component distributions and/or of the associations of mixture components with observations. Methods based on Gibbs sampling can easily be implemented for models based on conjugate prior distributions, but when non-conjugate priors are used, as is appropriate in many contexts, straightforward Gibbs sampling requires that an often difficult numerical integration be performed.
 Anmerkungen Die Quelle wird nach diesem Abschnitt genannt, aber nicht als Quelle eines Zitates oder Gedanken und auch nicht im Zusammenhang mit diesem Abschnitt. Sichter (Hindemith), KnallErbse

 Bearbeitet: 31. July 2012, 19:40 Graf IsolanErstellt: 26. July 2012, 00:37 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 141, Zeilen: 20-26
Quelle: Sohn Xing 2007
Seite(n): 1306, Zeilen: 31-39
Consider in particular an urn that at the outset contains a ball of a single color. At each step we either draw a ball from the urn and replace it with two balls of the same colour, or we are given a ball of a new colour which we place in the urn. The parameter a defines the probabilities of these two cases. Viewing each (distinct) color as a sample from G0 and each ball as a sample from G, Blackwell and MacQueen (1973) showed that this Polya urn model yields samples whose distributions are those of the marginal probabilities under the Dirichlet process. Consider an urn that at the outset contains a ball of a single color. At each step we either draw a ball from the urn and replace it with two balls of the same color, or we are given a ball of a new color which we place in the urn. [...] Letting parameter τ define the probabilities of the two types of draws, and viewing each (distinct) color as a sample from Q0, and each ball as a sample from Q, Blackwell and MacQueen [1973] showed that this Pólya urn model yields samples whose distributions are those of the marginal probabilities under the Dirichlet process.
 Anmerkungen Ohne Quellenverweis Sichter (Hindemith), KnallErbse

 Bearbeitet: 31. July 2012, 19:07 Graf IsolanErstellt: 28. July 2012, 10:45 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 24, Zeilen: 1-2
Quelle: Degen 2006
Seite(n): 18, Zeilen: 10-13
[In doing so we do not only get simpler expressions but also, and this is even more important, we can separate dependence] aspects from marginal distributions features. Marginals are handled using univariate Frèchet random variables, whereas the dependence structure needs some closer consideration. In doing so we do not only get simpler expressions but also, and this is even more important, we can separate dependence aspects from marginal distributions features. Margins are handled using univariate EVT, whereas the dependence structure needs some closer consideration.
 Anmerkungen Forsetzung von Rh/Fragment 023 33. Keine Kennzeichnung der Übernahme, kein Hinweis auf die Quelle. Das in den Zeilen 5-17 gegebene Theorem 2.3.2 stimmt in der Formulierung dann ebenfalls fast vollständig mit Theorem 2.1 von Degen (2006) - dort S.19, Z. 1-12 - überein. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 31. July 2012, 19:05 Graf IsolanErstellt: 28. July 2012, 10:37 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 23, Zeilen: 33-36
Quelle: Degen 2006
Seite(n): 18, Zeilen: 7-12
In order to give a characterization of max-stable distributions or equivalently of limit distributions for appropriately multivariate extreme value models, it is an enormous help to first standardize the problem so that G has specified marginals Gj. In doing so we do not only get simpler expressions but also, and this is even more important, we can separate dependence [aspects from marginal distributions features.] In order to give a characterisation of max-stable distributions or equivalently of limit distributions for appropriately normalised and centered multivariate maxima we note that it is an enormous help to first standardise the problem so that H has specified margins Hi. In doing so we do not only get simpler expressions but also, and this is even more important, we can separate dependence aspects from marginal distributions features.
 Anmerkungen keine Kennzeichnung der Übernahme, kein Quellenverweis. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 31. July 2012, 19:04 Graf IsolanErstellt: 28. July 2012, 10:23 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 23, Zeilen: 14-17
Quelle: Degen 2006
Seite(n): 17, Zeilen: 7-10
Max-stable distributions form a subclass of max-infinitely divisible (max-id) distributions which is the class of all distribution functions G, such that for all t > 0, Gt is again a distribution function. For some basic facts about max-stability and max-infinite divisibility see Resnick (1987); Falk et al. (2004). Max-stable distributions form a subclass of max-infinitely divisible (max-id) distributions which is the class of all distribution functions F, such that for all t > 0, Ft is again a distribution function. For some basic facts about max-stability and maxinfinite divisibility see Appendix A.
 Anmerkungen keine Kennzeichnung der Übernahme, keine Angabe der Quelle. Bemerkenswert ist, dass - wie in der Vorlage - unmittelbar auf die mathematische Aussage ein Verweis auf eine weitere Quelle für "basic facts" folgt. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 31. July 2012, 16:32 WiseWomanErstellt: 25. July 2012, 22:49 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 23, Zeilen: 24-32
Quelle: Degen 2006
Seite(n): 18, Zeilen: 1-6
2.3.2. Characterization of multivariate extreme value distributions. In contrast to the univariate case, the multivariate extreme value distributions cannot be represented by a parametric family indexed by a finite-dimensional parameter vector, the class of dependence structures is simply too large. Instead the family of multivariate extreme value distributions can be indexed by a class of finite measures; exponent measures (Starica (1999); Heffernan and Resnick (2005); Resnick (2006); Balkema and Embrechts (2007)) or in another description by a class of dependence functions as the Pickands dependence functions (Kotz and Nadarajah (2002); Klüppelberg and Mayer (2006)) or Copulas functions (Joe (1997); Embrechts et al. (2003); Nelsen (2006)). 2.1.2 Characterisation of MEVDs

A major difference to the univariate case is that multivariate extreme value distributions cannot be represented by a parametric family indexed by a finite-dimensional parameter vector — the class of dependence structures is simply too large. Instead the family of MEVDs can be indexed by a class of finite measures (exponent measures) or in another description by a class of convex functions (Pickands dependence functions).

 Anmerkungen The main text is supplemented with extensive literature references. Just the same, the phrasing of the text and the source is identical, not marked and without a reference. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 31. July 2012, 16:15 WiseWomanErstellt: 25. July 2012, 21:41 (Graf Isolan)

 Typus KomplettPlagiat Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 17, Zeilen: 15-18
Quelle: Boldi 2004
Seite(n): 22-23, Zeilen: S.22,23-25 - S.23,1-2
The Peaks Over Threshold method can be represented as a semi-parametric model. The excesses above a high threshold u are distributed according to a GPD, while the empirical distribution function of F, or any other appropriate model, is used under the threshold u. This is the semi-parametric extremal model, see for example Coles and Tawn (1991). [Seite 22]

The Peaks Over Threshold method can be represented as a semi-parametric model. The excesses above a high threshold u are distributed according to a generalized Pareto distribution while the empirical distribution function F, or any other appropriate model, is

[Seite 23]

used under u. This is the semi-parametric extremal model, see for example Coles & Tawn (1991).

 Anmerkungen fast identisch ohne Quellenangabe; lediglich "generalized Pareto distribution" wurde durch "GPD" ersetzt. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 31. July 2012, 16:10 WiseWomanErstellt: 26. July 2012, 18:49 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 176, Zeilen: 1-6
Quelle: Bojan 2000
Seite(n): 5, Zeilen: 14-15, 21-23
Two classes of distributions have gained particular popularity for modelling extreme events: regularly varying distributions and subexponential distributions. This chapter concentrates only on the first class, for which many real-life data sets in teletraffic, insurance and finance exist empirical evidence in favour.

Nowadays, there are several books on this theory (Bingham et al. (1987); Resnick (1987); Embrechts et al. (1997); Resnick (2006)).

Two classes of distributions have gained particular popularity for modelling extremal events: regularly varying distributions and subexponential distributions.

[...]

For many real-life data sets in teletraffic, insurance and finance there exists empirical evidence in favour of regularly varying distributions, see for instance Embrechts, Kluppelberg and Mikosch [25].

 Anmerkungen "Embrechts et al. (1997)" = "Embrechts, Kluppelberg and Mikosch [25]" Übereinstimmung ohne Kennzeichnung der Übernahme oder Quellenangabe. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 31. July 2012, 16:10 WiseWomanErstellt: 24. July 2012, 08:04 (Plagiatsfischer)

 Typus KomplettPlagiat Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 2, Zeilen: 23-25
Quelle: Fama 1965
Seite(n): 50, Zeilen: 5-10 (Left column)
In fact, under the Gaussian hypothesis for any given stock, an observation more than five standard deviations from the mean should be observed about once every 7,000 years! Similarly, under the Gaussian hypothesis for any given stock an observation more than five standard deviations from the mean should be observed about once every 7,000 years.
 Anmerkungen Sichter (Plagiatsfischer), KnallErbse

 Bearbeitet: 31. July 2012, 16:07 WiseWomanErstellt: 24. July 2012, 01:55 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 180, Zeilen: 9-14
Quelle: Bojan 2000
Seite(n): 23, 24, Zeilen: 23-26, 1-4
In practice one is often confronted with multivariate problems on a variety of stock or bond indices, or, perhaps the same assets in different markets. A multivariate concept of regular variation then will be needed. However, the extension of a mathematical notion from the one dimensional to the higher dimensional case often leads to a great variety of different approximations. The great majority of the results to be presented is known and can be found in Bingham et al. (1987); [...] In practice one is often confronted with multivariate data: on a particular day not only one but a variety of stock indices is reported, or, perhaps the price of the stock is determined in different markets. A multivariate concept of regular variation will be needed. However, the extension of a mathematical notion from

[Page 24]

the one-dimensional to the higher-dimensional case often leads to a great variety of different notions. [...] The great majority of the results to be presented is known and can be found in Bingham et al. [7] [...]

 Anmerkungen A source is not given. Sichter (Hindemith), KnallErbse

 Bearbeitet: 31. July 2012, 16:04 WiseWomanErstellt: 23. July 2012, 22:55 (Plagiatsfischer)

 Typus Verschleierung Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 2, Zeilen: 1-3
Quelle: Bojan 2000
Seite(n): 2, Zeilen: 28-31
This transformation is commonly used in finance (see for example Jorion (2003)). There are several reasons for this choice of transformation. The most important one is the belief that log-returns, in contrast to prices, can be understood as realization of a stationary process. This transformation is commonly used in finance (see Taylor [65]). There are several reasons for this choice of transformation. The first one is that one believes that log-returns, in contrast to prices, can be understood as realisation of a stationary process.
 Anmerkungen This must be seen in connection with the last line of the previous page, which is from the same source (Bojan 2000). Note that one of the standard sources (Taylor 65) has been replaced by another standard source (Jorion 2003). Both sources are relatively useless without page numbers. Jorion 2003 is a book of many hundred pages. Sichter (PlagiatsFischer), KnallErbse

 Bearbeitet: 31. July 2012, 15:58 WiseWomanErstellt: 5. July 2012, 08:34 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 85, Zeilen: 16-17
Quelle: Galbraith Zernov 2006
Seite(n): 1, Zeilen: Abstract, Zeile 16-18
More generally, the study of extreme dependence may reveal contrasts which are obscured when we only concentrate on examining the conditional second moment. More generally, the study of extreme dependence may reveal contrasts which are obscured when examining the conditional second moment.
 Anmerkungen Zur Plagiatseinordnung siehe Diskussion Sichter (Hindemith), KnallErbse

 Bearbeitet: 31. July 2012, 15:55 WiseWomanErstellt: 5. July 2012, 08:27 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 85, Zeilen: 33-36
Quelle: Galbraith Zernov 2006
Seite(n): 1, Zeilen: 3-10
While these models imply some information about extreme events still little is known about the extremes per se. For this reason, it is an advantage to have techniques that are focused purely on extreme movements, and are not influenced by the degree of temporal dependence in more routine circumstances. The resulting information about the degree to [which extreme losses are more likely following earlier extreme losses is particularly valuable in the measurement of risk over fixed time intervals.] While this knowledge implies some information about extreme events in these markets [...] relatively little is known about the extremes per se of these asset return distributions. In learning about dependence in extreme circumstances, it is an advantage to have techniques that are focused purely on extreme movements, and are not influenced by the degree of temporal dependence in more routine circumstances. The resulting information about the degree to which extreme losses are more likely following earlier extreme losses is particularly valuable in the measurement of risk over fixed time intervals.
 Anmerkungen There is no source given. Sichter (Hindemith), KnallErbse

 Bearbeitet: 31. July 2012, 15:54 WiseWomanErstellt: 4. July 2012, 20:40 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 186, Zeilen: 7-10
Quelle: Draisma et al. 2003
Seite(n): 1, Zeilen: Abstract
In the classical setting of bivariate extreme value theory, the procedures to estimate the probability of an extreme event are not applicable if the componentwise maxima of the observations are asymptotically independent. In the classical setting of bivariate extreme value theory, the procedures to estimate the probability of an extreme event are not applicable if the componentwise maxima of the observations are asymptotically independent.
 Anmerkungen This is an exact copy, there is no reference to a source. Sichter (Hindemith), KnallErbse

 Bearbeitet: 31. July 2012, 15:53 WiseWomanErstellt: 4. July 2012, 18:52 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 174, Zeilen: 8-13
Quelle: Embrechts_et_al._1999
Seite(n): 1, Zeilen: 11-16
On one hand the conditional correlation lies at the heart of the capital asset pricing model (CAPM) and the arbitrage pricing theory (APT), where its use as a measure of dependence between financial instruments is essentially founded on an assumption of multivariate normally distributed returns. Increasingly, however, correlation is being used as a dependence measure in general risk management, often in areas where the assumption of multivariate normal risks is completely untenable. Correlation lies at the heart of the capital asset pricing model (CAPM) and the arbitrage pricing theory (APT), where its use as a measure of dependence between financial instruments is essentially founded on an assumption of multivariate normally distributed returns. Increasingly, however, correlation is being used as a dependence measure in general risk management, often in areas where the assumption of multivariate normal risks is completely untenable
 Anmerkungen A source is not given. Sichter (Hindemith), KnallErbse

 Bearbeitet: 31. July 2012, 15:51 WiseWomanErstellt: 4. July 2012, 13:54 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 136, Zeilen: 16-18
Quelle: Morales_2005
Seite(n): 23, Zeilen: 18-20
The results of Smith and Weissman (1996) allow us to characterize the extremal behaviour of a multivariate stationary time series in terms of a limiting max-stable process. However, there has been little work on the statistical modelling of max-stable processes. The results of Smith and Weissman (1996) allow us to characterize the extremal behavior of a multivariate stationary time series in terms of a limiting max-stable process. However, there has been little work on the statistical modeling of max-stable processes.
 Anmerkungen No source given. Sichter (Hindemith), KnallErbse

 Bearbeitet: 31. July 2012, 15:43 WiseWomanErstellt: 24. July 2012, 21:03 (Plagiatsfischer)

 Typus KomplettPlagiat Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 11, Zeilen: 27-28
Quelle: Fougères 2004
Seite(n): 1, Zeilen: 26-27
Useful representations in terms of maxstable distributions, regular variation functions, or point processes, have been established. Useful representations in terms of maxstable distributions, regular variation functions, or point processes, have been established.
 Anmerkungen Ohne Quellenangabe Sichter KnallErbse

 Bearbeitet: 31. July 2012, 15:18 WiseWomanErstellt: 4. July 2012, 13:40 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 11, Zeilen: 20-26
Quelle: Morales_2005
Seite(n): 7, Zeilen: 3-13
In this section we review the basic background for univariate and multivariate extreme value theory for iid random variables, as well as the corresponding theory for stationary processes. There is a rich literature on extreme value theory that goes back to the 1920s. Recent introductory books for the univariate case on the subject are Coles (2001), which emphasizes statistical modelling, and Embrechts et al. (1997), which is a comprehensive reference for the theory and its applications to insurance and finance. Leadbetter et al. (1983) is mostly concerned with extremes of stationary processes. In this Chapter we review the basic background for univariate and multivariate extreme value theory for iid random variables, as well as the corresponding theory for stationary processes.

There is a rich literature on extreme value theory that goes back to the 1920’s. Recent introductory books on the subject are Coles (2001), which emphasizes statistical modeling,[...] Embrechts, Klüppelberg and Mikosch (1997) is a comprehensive reference for the theory and its applications to insurance and finance. [...] Leadbetter, Lindgren and Rootzén (1983) is mostly concerned with extremes of stationary processes.

 Anmerkungen The literature review is taken from the source, shortening it slightly. Sichter (Hindemith), KnallErbse

 Bearbeitet: 30. July 2012, 23:33 HindemithErstellt: 26. July 2012, 11:59 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 208, Zeilen: 15-21
Quelle: Gonzalez-Hermosillo 2008
Seite(n): 102, Zeilen: 16-22
Furthermore, if the structure of transmission mechanisms is found to be common across different times of crises, this would suggest that all crises are indeed alike regardless of the nature of the initial shock and the economic and institutional environments of the affected country. Alternatively, if the propagation mechanisms vary across crises, perhaps as a result of the development of new strains of contagion, this would suggest that crises are indeed unique at least across their source and their transmission mechanics. If the structure of these three transmission mechanisms is found to be common across different financial crises, this would suggest that all crises are indeed alike regardless of the nature of the initial shock and the economic and institutional environments of the affected country. Alternatively, if the propagation mechanisms vary across crises, perhaps as a result of the development of new strains of contagion, this would suggest that crises are indeed unique at least across their source and their transmission mechanism.
 Anmerkungen Die Quelle ist nicht angegeben. Sichter (Hindemith), Graf Isolan

 Bearbeitet: 30. July 2012, 23:32 HindemithErstellt: 24. July 2012, 01:41 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 175, Zeilen: 36-39
Quelle: Bojan 2000
Seite(n): 5, Zeilen: 5-9
In a first approximation one may describe a regular varying distribution at infinity as one whose tails are much heavier than those of the normal or exponential distributions. Historically, a precise definition as “heavy" or “ light" tails very much depends on the area of application and the structural properties of the time series one wants to model. Heuristically, we may describe a "heavy-tailed" distribution as one whose tails are much heavier than those of the normal or exponential distributions. Historically, a precise definition of "heavy" or "light" tails very much depends on the area of application and the structural properties of the time series one wants to model.
 Anmerkungen Slightly adapted. The source is not referenced. Sichter (Hindemith), Graf Isolan

 Bearbeitet: 30. July 2012, 23:32 HindemithErstellt: 25. July 2012, 23:32 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 150, Zeilen: 10-18
Quelle: Chen et al. 2006
Seite(n): 8 (preprint), Zeilen: 26-36
5.5.5. Prediction. The calculation of the predictive probability of new data will be averaged over a number of MCMC samples, which are selected from those samples where the algorithm tends to stabilize. Stabilization will be assessed heuristically based on the value of the log-likelihood. Additionally to eliminate the auto-correlation, one sample will be selected from each consecutive set of 10 iterations. For a particular MCMC sample, the predictive probability is attained from two components: the represented and the unrepresented mixtures. In a similar manner to that adopted in the sampling stage, the probability from unrepresented mixtures will be approximated by a finite mixture of Gaussians, whose parameters (&#x03BCl, &#x03A9l) are drawn from the prior. 2.4 Prediction

The calculation of the predictive probability of new data will be averaged over a number of MCMC samples, which are selected from those where the algorithm tends to stabilize. Stabilization will be assessed heuristically based on the value of the log-likelihood. Additionally to eliminate the auto-correlation, one sample will be selected from each consecutive set of 10 iterations.

For a particular MCMC sample, the predictive probability is attained from two components: the represented and the unrepresented mixtures. In a similar manner to that adopted in the sampling stage, the probability from unrepresented mixtures will be approximated by a finite mixture of Gaussians, whose parameters, (&#x03BCj, &#x03C4j) are drawn from the prior.

 Anmerkungen identisch; ohne Kennzeichnung und ohne Quellenangabe. Sichter (Graf Isolan), KnallErbse, Hindemith

 Bearbeitet: 30. July 2012, 23:32 HindemithErstellt: 25. July 2012, 23:36 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 137, Zeilen: 5-13
Quelle: Rasmussen et al. 2007
Seite(n): 3, Zeilen: 22ff
We describe an approach to the problem of automatically determine [sic] the number patterns L based on the theory of infinite Gaussian mixtures or Dirichlet process mixtures. This theory is based on the observation that the mathematical limit of an infinite number of components in an ordinary finite mixture model (i.e. the patterns L in the d-dimensional model) corresponds to a Dirichlet process prior. In an infinite Gaussian mixture model there is no need to make arbitrary choices about how many patterns L there are in the process. The major advantage is that, although in theory the infinite mixture model has an infinite number of parameters, it is possible to do exact inference in these infinite mixture models efficiently using Markov chain Monte Carlo (MCMC) methodology. We describe an approach to the problem of automatically clustering microarray gene expression profiles based on the theory of infinite Gaussian mixtures (or Dirichlet process mixtures (DPM)) [5], [6]. This theory is based on the observation that the mathematical limit of an infinite number of components in an ordinary finite mixture model (i.e. clustering model) corresponds to a Dirichlet process prior [5]–[7]. In an infinite Gaussian mixture model there is no need to make arbitrary choices about how many clusters there are in the data. Although in theory the infinite mixture model has an infinite number of parameters, surprisingly, it is possible to do exact inference in these infinite mixture models efficiently using Markov chain Monte Carlo (MCMC) methodology, [...]
 Anmerkungen Die Quelle wird nicht erwähnt. Zur Anpassung des Untersuchungsgegenstandes werden einige Stichwortersetzungen vorgenommen. Dabei scheinen sich im ersten Satz sprachliche Fehler eingeschlichen zu haben. Sichter (Hindemith), KnallErbse

 Bearbeitet: 30. July 2012, 23:31 HindemithErstellt: 26. July 2012, 14:21 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 158, Zeilen: 1-3
Quelle: Haxel 2009
Seite(n): 1 (internet version), Zeilen: -
The DAX Index has tumbled 45 percent since the beginning of last year as credit losses and writedowns topped $1 trillion in the worst financial crisis since the Great Depression and together with countries like the U.S., Japan and Europe fell into simultaneous recessions. The DAX Index has tumbled 45 percent since the beginning of last year as credit losses and writedowns topped$1 trillion in the worst financial crisis since the Great Depression and the U.S., Japan and Europe fell into simultaneous recessions.
 Anmerkungen keine Kennzeichnung als Zitat; keine Quellenangabe Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 30. July 2012, 23:31 HindemithErstellt: 26. July 2012, 16:43 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 154, Zeilen: 20-22
Quelle: Beulig et al. 2008
Seite(n): I, Zeilen: 3-5
The subprime mortgage financial crisis is an ongoing crisis which was caused by the sharp rise in the US subprime mortgage market that began in the United States in fall 2006 and became to a global financial crisis in July 2007. The subprime mortgage financial crisis is an ongoing financial crisis which was caused by the sharp rise in the US subprime mortgage market that began in the United States in fall 2006 and became to a global financial crisis in July 2007
 Anmerkungen Ungekennzeichnete wortwörtliche Übernahme ohne Nennung der Quelle. Man beachte den übereinstimmenden Formulierungsfehler "became to a global financial crisis", der deutlich darauf hinweist, dass hier reines Copy&Paste vorliegt. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 30. July 2012, 23:31 HindemithErstellt: 26. July 2012, 18:09 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 165, Zeilen: 4-8
Quelle: Hilbers und Jones 2004
Seite(n): 1, Zeilen: 9-11, 15-17
The rescent international financial turmoil has prompted the development of new frameworks, risk tools, and techniques to assess the stability of financial systems. But what happens if an actual shock hits the system - how will the system perform? Multivariate extreme value theory can be used as an additional instrument in the financial sector to help answer such questions. The international financial turmoil of the 1990s prompted the development of new frameworks, tools, and techniques to assess the stability of financial systems. [...] But what happens if an actual shock hits the system — how will the system perform? Stress tests can be used as an additional instrument in the toolbox of financial sector watchdogs to help answer such questions.
 Anmerkungen Dem Thema angepasst, aber die ungekennzeichnete wörtliche Übereinstimmung ist deutlich sichtbar. In dem Teil, der nicht übernommen wurde, findet sich dann auch ein Rechtschreibfehler ("rescent"). Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 30. July 2012, 23:31 HindemithErstellt: 28. July 2012, 00:04 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 163, Zeilen: 16-23
Quelle: Guo_2008
Seite(n): 3, Zeilen: 29ff
Stress testing techniques fall into two general categories: sensitivity tests and scenario tests. Sensitivity tests assess the impact of large movements in financial variables on portfolio values without specifying the reasons for such movements. A typical example might be a 10% decline in some stock market index as the Volkswagen. These tests can be run relatively quickly and are commonly used as a first approximation of the portfolio impact of a financial market move. However, the infinite number of scenarios, the analysis lacks historical and economic content can limit its usefulness for longer term risk-management decisions. Stress-testing techniques fall into two general categories: sensitivity tests and scenario tests. Sensitivity tests assess the impact of large movements in financial variables on portfolio values without specifying the reasons for such movements. A typical example might be a 100 basis point increase across the yield curve or a 10 percent decline in stock market indexes. These tests can be run relatively quickly and are commonly used as a first approximation of the portfolio impact of a financial market move. However, the analysis lacks historical and economic content, which can limit its usefulness for longer term risk management decisions.
 Anmerkungen Ein Quellenverweis fehlt. Diese Stelle findet sich auch in der früheren, alternativen Quelle: FRBSF 2005 Sichter (Hindemith), KnallErbse

 Bearbeitet: 30. July 2012, 23:31 HindemithErstellt: 28. July 2012, 14:38 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 206, Zeilen: 29-32
Quelle: Rodriguez 2003
Seite(n): 1, Zeilen: 2-4, 101-102
It is a central issue in asset allocation and risk management is whether financial markets become more interdependent during financial crises. This issue acquired dramatic importance during the last crises, as the Russian default in 1998, the devaluation of the Brazilian real in 1999, or the most recent Subprime Crisis (2007- 2009). A central issue in asset allocation and risk management is whether financial markets become more interdependent during financial crises. This issue acquired dramatic importance during the five major crises of the 1990’s1.

1 These were the ERM attacks (1992), the Mexican devaluation (1994), the East Asian crisis (1997), the Russian default (1998), and the devaluation of the Brazilian real (1999).

 Anmerkungen kein Hinweis auf eine Übernahme, keine Quellenangabe. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 30. July 2012, 23:31 HindemithErstellt: 29. July 2012, 10:55 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 138, Zeilen: 8-15
Quelle: Hoffman et al. 2008
Seite(n): 2 (Exzerpt), Zeilen: 1. Spalte: 33ff
Notice that popular tables become less and less likely to sit down at a new table. In this representation the dishes correspond to probability density functions, and the process of ordering a dish l corresponds to drawing the parameters &#x03C6l to a probability density function, as for example a Gaussian from a prior distribution G over those parameters. The process of a customer l choosing a table cl corresponds to choosing a distribution &#x03C6cl from which to draw an observation yl. Since the structure of the process, is that customers tend to sit at tables with many other customers producing the cluster behaviour, thought it has an infinite number of mixture components to choose from. Notice that popular tables become more popular, and that as more customers come in they become less and less likely to sit down at a new table.

[...]. The “dishes” in the CRP correspond to probability density functions, and the process of “ordering” a dish k corresponds to drawing the parameters &#x03C6k to a PDF from a prior distribution H over those parameters. (For example, each dish k can be a Gaussian with parameters {&#x03BCk, &#x03A3k}= &#x03C6k ~ H.) The process of a customer t choosing a table zt corresponds to choosing a distribution &#x03C6zt from which to draw an observation yt [...]. Since customers in the CRP tend to sit at tables with many other customers, the DPMM tends to draw points from the same mixture components again and again even though it has an infinite number of mixture components to choose from.

 Anmerkungen Kein Quellenverweis zu finden, obwohl der Text weitgehend wörtlich mit der Quelle übereinstimmt (wobei die Variablen anders benannt sind). Man beachte den sinnlosen ersten Satz in der Dissertation, der aber trotzdem wörtlich mit Satzfragmenten aus der Quelle übereinstimmt. Sichter (Hindemith), WiseWoman

 Bearbeitet: 30. July 2012, 23:19 HindemithErstellt: 4. July 2012, 18:10 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 11, Zeilen: 10-19
Quelle: Gonzalo_Olmo_2004
Seite(n): 349, 350, Zeilen: 20-27, 1-5
The question one try to answer is: If things go wrong, how wrong can they go? The variance used as a risk measure is unable to answer this question. Alternative measures regarding possible values out of the range of available information need to be defined and calculated. Extreme value theory (EVT) provides the tools to model the asymptotic distribution of the maximum of a sequence of random variables Xi, and in this sense this theory can be very helpful in order to get a first impression about how wrong things can go. A deeper insight into EVT allows knowing not only the order of convergence of the maximum but also the limiting distribution of the largest observations of the sequence. These observations are the main ingredients of more informative risk measures that are normally utilized, like Value at Risk (VaR) or Expected Shortfall. The question one would like to answer is: ‘‘If things go wrong, how wrong can they go?’’ The variance used as a risk measure is unable to answer this question.

Alternative measures regarding possible values out of the range of available information need to be defined and calculated. Extreme value theory (EVT) provides the tools to model the asymptotic distribution of the maximum of a sequence of random variables {Xn}, and in this sense this theory can be very helpful in order to obtain a first impression about how wrong things

[page 350]

can go. A deeper insight into EVT allows us to know not only the order of convergence of the maximum, but also the limiting distribution of the largest observations of the sequence. These observations are the main ingredients of more informative risk measures that have been recently introduced, like value at risk (VaR) or expected shortfall.

 Anmerkungen Source is not given. Minimally adjusted. Sichter (Hindemith), KnallErbse

 Bearbeitet: 30. July 2012, 23:18 HindemithErstellt: 23. July 2012, 00:01 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 1, Zeilen: 6-8
Quelle: Chavez-Demoulin_Embrechts_2010
Seite(n): 2, Zeilen: 2-4
The current subprime crisis, together with its consequences for international markets, shows that a deeper understanding of extreme events in statistical data from economics, insurance and finance is of high priority. The current subprime crisis, together with its consequences for international markets, shows that a deeper understanding of extreme events in statistical data from economics, insurance and finance is of high priority.
 Anmerkungen no source given Sichter (Hindemith), KnallErbse

 Bearbeitet: 30. July 2012, 23:18 HindemithErstellt: 23. July 2012, 21:31 (Plagiatsfischer)

 Typus Verschleierung Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 1, Zeilen: 18-22
Quelle: Schmidt 2003
Seite(n): 6, Zeilen: 9-13
Extreme events refer, for example, to extraordinary claims to insurance companies, crashes of equity markets or extreme losses in credit portfolios due to borrower defaults. Hence, extreme events occur rarely, i.e., only few extreme observations are available. Nevertheless, probabilities and dependence structures have to be assigned to extreme events due to their economic impact. Extreme events refer, for example, to extraordinary claims to insurance companies, crashes of equity markets, or extreme losses in credit portfolios due to borrower defaults. Hence, extreme events occur rarely, ergo, only few extreme observations are available; but probabilities and dependence structures have to be assigned to extreme events due to their economic impact.
 Anmerkungen Ohne Quellenangabe Sichter KnallErbse

 Bearbeitet: 30. July 2012, 23:18 HindemithErstellt: 23. July 2012, 21:57 (Plagiatsfischer)

 Typus Verschleierung Bearbeiter Plagiatsfischer Gesichtet
Untersuchte Arbeit:
Seite: 1, Zeilen: 23-26
Quelle: Kole 2006
Seite(n): 1, Zeilen: 16-20
In this dissertation we study a variety of crises and crashes from the perspective of an investor in financial markets. The two key concerns that an investor has regarding crises and crashes are their influence on his risk exposure and their effect on his asset allocation decisions. This thesis analyzes these aspects in several ways. In this dissertation we study crises and crashes from the perspective of an investor in financial markets. The two key concerns that an investor has regarding crises and crashes are their influence on his risk exposure and their effect on his asset allocation decisions. We analyze these questions in several ways.
 Anmerkungen Ohne Quellenangabe Sichter KnallErbse

 Bearbeitet: 30. July 2012, 23:18 HindemithErstellt: 25. July 2012, 22:11 (Graf Isolan)

 Typus KomplettPlagiat Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 22, Zeilen: 18-24
Quelle: Smith 1990
Seite(n): 2, Zeilen: 8-17
The probabilistic limit theory of multivariate extremes is reasonably well established, and has been reviewed in the books of Resnick (1987) and Galambos (1975), but statistical theory is still in rapid development. Coles and Tawn (1991, 1994) have proposed methods based on multivariate extreme value distributions, which therefore generalize the classical approach to univariate extremes based on the limiting extreme value distributions, while Coles and Tawn (1999), proposed methods extending the threshold-exceedances approaches developed in Smith (1989). The probabilistic limit theory of multivariate extremes is reasonably well established, and has been reviewed in the books of Resnick (1987) and Galambos (1987), but statistical theory is still in rapid development. Tawn (1988, 1990a) and Smith, Tawn and Yuen (1990) have proposed methods based on multivariate extreme value distributions, which therefore generalise the classical approach to univariate extremes based on the limiting extreme value distributions (Gumbel 1958), while Coles and Tawn (1991) and Joe, Smith and Weissman (1991) proposed methods extending the threshold-exceedances approaches developed in Smith (1989) and Davison and Smith (1990).
 Anmerkungen bis auf die teilweise anderen Literaturverweise identisch; keine Quellenangabe. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 30. July 2012, 23:18 HindemithErstellt: 27. July 2012, 21:06 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 5, Zeilen: 22-26
Quelle: Smith 1990
Seite(n): 2, Zeilen: 7-11
A more appropriate framework is multivariate extreme value theory, which has been developed for studying the joint distribution of extremes in several series. The probabilistic limit theory of multivariate extremes is reasonably well established, and has been reviewed in the books of Galambos (1975); Resnick (1987); Coles and Tawn (1991); Falk et al. (2004), but the statistical theory is still in rapid development. Multivariate extreme value theory has been developed to study the joint distribution of extremes in several series. The probabilistic limit theory of multivariate extremes is reasonably well established, and has been reviewed in the books of Resnick (1987) and Galambos (1987), but statistical theory is still in rapid development.
 Anmerkungen Die Literatur wurde um einige neuere Werke ergänzt, ansonsten weitgehend wörtliche Übernahme ohne Quellenverweis. Sichter (Hindemith), KnallErbse

 Bearbeitet: 30. July 2012, 23:18 HindemithErstellt: 28. July 2012, 12:56 (Hindemith)

 Typus KomplettPlagiat Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 4, Zeilen: 9-11
Quelle: Zivot_2005
Seite(n): 1, Zeilen: 15-16
In these models volatility is usually extracted from daily squared returns, which are unbiased but noisy estimates of daily conditional volatility. In these models volatility is usually extracted from daily squared returns, which are unbiased but noisy estimates of daily conditional volatility
 Anmerkungen Sehr kurz, aber eindeutig übernommen. Siehe auch Rh/Fragment 085 12 Sichter (Hindemith), KnallErbse

 Bearbeitet: 30. July 2012, 23:18 HindemithErstellt: 28. July 2012, 13:02 (Hindemith)

 Typus Verschleierung Bearbeiter Hindemith Gesichtet
Untersuchte Arbeit:
Seite: 85, Zeilen: 12-15
Quelle: Zivot_2005
Seite(n): 1, Zeilen: 13-16
Popular parametric models for volatility include the ARCH-GARCH family (Engle (1982b)) and the stochastic volatility (SV) family (Clark (1973)). In these models volatility is usually extracted from daily squared returns, which are unbiased but noisy estimates of daily conditional volatility. Popular parametric models for latent volatility include the ARCH-GARCH family, the stochastic volatility family, and the Markov-switching family. In these models volatility is usually extracted from daily squared returns, which are unbiased but noisy estimates of daily conditional volatility.
 Anmerkungen Kein Quellenverweis vorhanden. Die eingebrachten Zitate scheinen auf Beispielliteratur zu verweisen, in denen diese Modelle angewendet wurden. Der zweite Satz wird noch einmal verwendet: Rh/Fragment 004 09 Sichter (Hindemith), KnallErbse

 Bearbeitet: 30. July 2012, 23:18 HindemithErstellt: 28. July 2012, 14:47 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 73, Zeilen: 2-3
Quelle: Rodriguez 2003
Seite(n): 5, Zeilen: 25
These results contribute to the ongoing debate on the existence of contagion from the point of view of the experimented extreme events. These results contribute to the ongoing debate on the existence of contagion.
 Anmerkungen Bis zum letzten Satz wird auf Fremdquellen zurückgegriffen. Keine Kennzeichnung der übernommenen Passage, kein Hinweis auf die Quelle. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 30. July 2012, 23:13 HindemithErstellt: 28. July 2012, 15:01 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 72, Zeilen: 27
Quelle: Rodriguez 2003
Seite(n): 5, Zeilen: 18-19
There is evidence of changing dependence structures during periods of financial turmoil. [...] I find evidence of changing dependence structures during periods of financial turmoil.
 Anmerkungen Vor den abschließenden langen Abschnitt aus Worthington et al. (2004) wird noch ein Satz aus Rodriguez (2003) gepresst. Damit besteht der gesamte interpretative Teil des Schlussabschnitt "Conclusions" des Kapitels 3 von Rh mit Ausnahme des ersten Satzes und der abschließenden adverbialen Bestimmung im letzten Satz (der mehrheitlich auch von Rodriguez stammt) ungekennzeichnet aus Fremdmaterial. Sichter (Graf Isolan), KnallErbse

 Bearbeitet: 30. July 2012, 22:23 HindemithErstellt: 27. July 2012, 20:15 (Graf Isolan)

 Typus Verschleierung Bearbeiter Graf Isolan Gesichtet
Untersuchte Arbeit:
Seite: 48, Zeilen: 14-17
Quelle: Drees 2007
Seite(n): 16, Zeilen: 11-15
Roughly speaking, these are functionals which depend on all shortest vectors of observations containing exceedances over a given high threshold. An asymptotic theory on estimators of functionals of that type would be a significant step forward towards a general approach to analyze the extremal dependence structure of stationary time series. Roughly speaking, these are functionals which depend only on all shortest vectors of observations containing exceedances over a given high threshold. An asymptotic theory on estimators of functionals of that type would be a significant step forward towards a general approach to analyze the extremal dependence structure of stationary time series.
 Anmerkungen keine Kennzeichnung als Zitat, kein Hinweis auf eine Quelle Sichter (Graf Isolan), KnallErbse