Statistical Analysis of Financial Data

Size: px
Start display at page:

Download "Statistical Analysis of Financial Data"

Transcription

1 ETH Zürich, WBL Angewandte Statistik 2017 Blockkurs Statistical Analysis of Financial Data Prof. Dr. Andreas Ruckstuhl Dozent für Statistische Datenanalyse Institut für Datenanalyse und Prozess Design IDP Zürcher Hochschule für Angewandte Wissenschaften ZHAW 30. Januar 2017 A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 1

2 Outline of Lecture 5 Lecture 1: Financial Data and Their Properties Lecture 2: Model for Conditional Heteroskedasticity and Risk Measures Lecture 3: Statistical Issues When Applying Portfolio Theory Lecture 4: (Financial) Factor Models Lecture 5: Copulas Basic Theory Gaussian and t-copulas Archimedean Copulas Rank Correlation Tail Dependence Calibrating Copulas (i.e., Estimating Copulas) *Vine Copula A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 2

3 8.1 Introduction The statistical analysis of multivariate Date is classically based on the multivariate normal distribution. As a consequence we need just to bother estimating the mean/expectation and the covariance matrix from the data. The stochastic dependence between two normally distributed variables is described by the covariance The covariance between two random variables depends on their variances as well as the strength of the linear relationship between them (see also slide 6, Part 3) To understand the relationship between variables, it is much better to examine their (sample) correlation matrix. A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 3

4 Example: Daily returns on two equities GE and IBM and on CRSP, a value-weighted index including dividends (Jan 3,1969 to Dec 31, 1998) > round(cor(stocks),3) > round(cov(stocks),6) ge ibm ge CRSP ibm CRSP ge e-05 ge ibm e-05 ibm CRSP e-05 CRSP Most people use the correlation matrix for examination: All sample correlations are positive The largest correlation is between CRSP and ge The correlation coefficients is only a summary of the linear relationship between variables. Interesting features, such as nonlinearity or the joint behaviour of extreme values, remain hidden A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 4

5 A way out of this shortcomings is the so-called scatterplot matrix: One sees little evidence of nonlinear relationships, but some structures caused by non-normal (i.e., non-gaussian) events. This lack of nonlinearities is typical of returns on equities, but it should not be taken for granted instead, one should always look at the scatterplot matrix. A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 5

6 8.2 Basic Theory Modelling multivariate distributions beyond normal distributions need an new approach to model dependencies (instead of correlations) A copula is a multivariate cumulative distribution function (CDF) whose univariate marginal distributions are all uniform [0,1] Remember: If Y has a continuous CDF F, then F(Y) has a Uniform(0,1) distribution T Suppose Y =(Y1,, Yd) has a multivariate CDF with continuous marginal univariate CDF Then the CDF of is a copula. This CDF is called the copula of Y and denoted by CY that is CY contains all information about dependencies among the components of Y but has no information about the marginal CDFs of Y. A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 6

7 Sklar s Theorem justifies the copula approach. It states that the joint CDF FY can be decomposed into the copula CY, which contains all information about the dependencies among (Y1,..., Yd), and the univariate marginal CDFs, which contain all information about the univariate marginal distributions. That is Motivation: For calibration we need an expression in terms of the joint density: The independence copula: A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 7

8 Example: Scatterplot of the three daily return series (GE, IBM and CRSP) (cf. slide 5) transformed to uniform marginals A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 8

9 8.3 Gaussian and t-copulas Using copulas to model multivariate dependencies, we need parametric families of copulas. The dependencies within Y is described by the correlation matrix Ω of Y since the copula does not depend on the univariate marginal distribution (including variance) Hence, the copula CY depends only on the correlation matrix Ω of Y The Gaussian copula with correlation matrix Ω will be denoted A distribution with a Gaussian copula is called a meta-gaussian distribution. This does not mean that Y has a multivariate Gaussian distribution, since the univariate distributions could be any distribution at all. Example: Meta-Gaussian distribution for 2 dimensions: Transform the marginal distribution to uniformity and apply a standard twodimensional Gaussian distribution with correlation ρ on it where Φ-1() is the inverse of the standard Gaussian distribution and Φ2(,, ρ) the bivariate distribution of two standard Gaussian distribution with correlation ρ A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 9

10 Example in R: Gaussian copula for 2 dim different marginals library(copula) nc1 <- normalcopula(0.8, dim=2) # define the copula model set.seed(5640) rnc1 <- rcopula(1000, nc1) # generate 1000 random numbers Margins: Gamma and beta distributed x <- qgamma(rnc1[,1],2) y <- qbeta(rnc1[,2],1,2) plot(x,y) # they correlate! A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 10

11 Meta-Gaussian distribution became enormously popular in the end causing problems because the market too strongly believed in it ( 2007 subprime crises) The Gauss-copula is the worst invention ever for credit risk management. (A risk Probabilist) see also t-copula Similarly, let be the copula of a multivariate t-distribution with correlation matrix Ω and degrees of freedom ν (The same for all dimensions). The shape parameter ν affects both the univariate marginal distribution and the copula, so ν is a parameter of the copula. A distribution with a t-copula is called a t-meta distribution. distribution A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 11

12 > library(copula) > tc1.3 <- tcopula(c(-.6,0.75,0), dim=3, dispstr="un", df=1) > set.seed(5640) > r.tc1.3 <- rcopula(500, tc1.3) > pairs(r.tc1.3) > cor(r.tc1.3) [,1] [,2] [,3] [1,] [2,] [3,] > tc25.3 <- tcopula(c(-0.6,0.75,0), dim=3, df=25) > set.seed(5640) > r.tc25.3 <- rcopula(500, tc25.3) > pairs(r.tc25.3) > cor(r.tc25.3) [,1] [,2] [,3] [1,] [2,] [3,] A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 12

13 8.4 Archimedean Copulas An Archimedean copula wit a strict generator has the form, ( ) where g() is the generator of the copula and satisfies g is continuous, strictly decreasing, convex mapping [0,1] onto [0, ) g(0)= and g(1)=0 Notice that in ( ), the value of C(u1,, ud) is unchanged if we permute u 1,, ud. One consequence of this property (called exchangeability) is: rank correlations (see later) are the same for all pairs of variables. Archimedian copulas are most useful in the bivariate case or in applications where we expect all pairs to have similar dependencies A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 13

14 Three generators for Archimedean copulas: Frank copula Generator: Inverse Generator: bivariate Frank copula: using ( ) θ=0 requires some care. Evaluate the limit of (bivariate) independence copula C0:, which yields the Clayton copula Generator Clayton copula The Clayton copula for θ=0 is defined as the independence copula C0. For -1 < θ < 0 the copula is not strict and there is no probability, e.g. for d=2: if u1 and u2 are both small then occurs. In theses cases, the Clayton copula is set equal to 0. A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 14

15 Gumbel copula Generator: Gumbel copula: The Gumbel copula is the independent copula when θ=1 but it cannot have negative dependence. Simulations On the next slides, simulation of bivariate samples are shown using scatterplots All simulations are with a sample size of 200 And with values of that give dependencies ranging from strongly negative (if possible) to strongly positive A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 15

16 Random samples from Frank copulas A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 16

17 Random samples from Clayton copulas A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 17

18 Random samples from Gumbel copulas A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 18

19 Some remarks to the simulation results: the Frank and Clayton copulas are rather different when the amount of dependence is somewhere between the extremes. In particular, the Clayton copula's exclusion of the region when -1 < θ < 0 is evident, especially in the example with θ=-07 The Frank copula is symmetric about the diagonal from (0, 1) to (1, 0), but the Clayton copula does not have this symmetry. It is clearly seen that the Gumbel copula cannot model negative dependencies. A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 19

20 8.5 Tail Dependence Tail dependence measures association between the extreme values of two random variables and depends only on their copula. Suppose that Y=(Y1, Y2)T is a bivariate random vector with copula CY. Lower Tail Dependence The coefficient of lower tail dependence is denoted by l and defined as ll := lim P Y2 FY-2 1 (q) Y1 FY-11 (q) = lim q 0 = lim q 0 P Y2 FY-2 1 (q ) and Y1 FY-11 (q ) P Y1 FY-11 (q ) q 0 P FY2 (Y2 ) q and FY1 (Y1 ) q P FY1 (Y1 ) q = lim q 0 CY (q, q ) q If Y1 and Y2 are independent, then Therefore, l = 0 implies that in the extreme left tail, Y1 and Y2 behave as they are independent. A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 20

21 Upper Tail Dependence The coefficient of upper tail dependence is defined analogously For Gaussian and t-copula, Knowing whether or not there is tail dependence is important for risk management. If there are no tail dependencies among the returns on the assets in a portfolio, then there is little risk of clusters of very negative returns, and the risk of an extreme negative return on the portfolio is low. Conversely, if there are tail dependencies, then the likelihood of extreme negative returns occurring simultaneously on several assets in the portfolio can be high. A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 21

22 Tail Dependence for Gaussian and t-copulas Gaussian Copula: λl= 0, if correlation is ρ 1. That is, Gaussian copulas do not have tail dependence except in case of ρ=1 T-Copula with correlation ρ: where Ft,ν+1 is the CDF of the t-distribution with (υ+1) degree of freedom. Since Ft,ν+1(- ) = 0, we see that λl 0 if υ (i.e., consistent with Gaussian Copula) Left: Coefficients of tail-dependence for some t-copulas A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 22

23 Tail Dependance of Archimedean copulas In case of d=2, it can be shown that The Gumbel copula is able to model upper tail dependency, but no lower, whereas The Calyton copula can model lower tail dependence, but no upper: The Frank copula is not able to model either tail dependencies. Financial markets: losses occur more often jointly than gains do A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 23

24 8.6 Calibrating Copulas (i.e., Estimating Copulas) Assume that we have an i.i.d. sample and we wish to estimate the joint distribution using a copula approach. An important task is choosing a copula model. An appropriate copula model can be selected using graphical techniques as well as with AIC (see below) after fitting The fitting of the selected model is based on the log-likelihood of (cf. Slide 7) A direct maximum likelihood estimation may be too challenging because the large number of parameter cause numerical problems if any of the marginals are not well fitted by a convenient parametric family, this may cause bias in the estimated parameters of both the marginals and the copula A pseudo-maximum likelihood estimation may be more convenient. It is a two-step process, where each part (red, green) is estimated separately A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 24

25 In a first step, each of the d marginal distribution functions are estimated, one at a time (green part): There are two approaches, parametrically and nonparametrically. Parametrically: Fit convenient parametric distribution functions to each of the marginal distributions using maximum likelihood estimators Nonparametrically: The marginal distribution is estimated by the empirical CDF: [The divisor (n+1) ensures that the maximum value of is (n/(n+1) < 1] In a second step, is maximised over the parameter of the copula Also the maximisation of this step can be difficult when is highdimensional. E.g., if one uses a t-copula, then there are d(d-1) correlation parameters good starting values are needed (see next slide) A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 25

26 8.6.1 Estimation of in the Meta-t-Distribution The Pearson correlation coefficient ρ measures the linear dependency between two random variables. A such it is not convenient for the copulas approach because It is not invariant under nonlinear strictly increasing transformations Hence, it depends on the univariate marginal distributions as well as the copula. Marginal distribution and correlation do not determine the joint distribution except in case of Gaussian marginals Rank correlation coefficients remedy this problem, since they depend only on the copula Spearman s rank correlation depends only on the copula because it is invariant to any monotonically increasing transformation of the random variables; hence under CDF transformation as well. It is calculated as Pearson correlation of the ranks of the variables and estimates the Pearson correlation of the CDF transformed variables: A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 26

27 Another version which is based on ranks is Kendall s tau Let are two copies of independent bivariate of random variables. Then are called a concordant pair if either. In either case, Similarly, if are called a disconcordant pair Kendall's tau is the probability of a concordant pair minus the probability of a discordant pair. Therefore, Kendall s tau for is The sample Kendall s tau of a bivariate sample is A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 27

28 Kendall s tau has the following relation to Ω: Hence we can use as estimate (or starting value) Unfortunately, this matrix may not be positive (semi-) definite. must be adjusted Determine the eigenvalues "λ" and eigenvectors of Calculate where E is the matrix of the eigenvectors and ε a small number > 0, e.g., ε =0.001 But now the diagonal elements of may not be equal to 1 Hence, a easy fix yields the final solution: multiply the ith row and the ith column of The final result is called A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 28

29 8.6.2 Example: Bivariate data set of returns on IBM and the CRSP index library(ecdat) data(crspday, package="ecdat") IBM <- as.numeric(crspday[,5]) CRSP <- as.numeric(crspday[,7]) ## Fitting marginal t-distributions using package QRM > library(qrm) > IBM.tfit <- fit.st(ibm) ## fit a "scale-location" t-distribution > (IBM.est <- IBM.tfit$par.ests) nu mu sigma > CRSP.tfit <- fit.st(crsp) >(CRSP.est <- CRSP.tfit$par.ests) nu mu sigma ## Transformation of the data to uniform margins pstd <- function (q, mean=0, sigma=1, nu = 5) { # X U ## sd=sigma*s with s=sqrt(nu/(nu - 2)) z <- (q mean)/sigma ## i.e., sd(z) = sqrt(nu/(nu - 2)) pt(q = z, df = nu) } UD <- cbind(pstd(ibm, IBM.est["mu"], IBM.est["sigma"], IBM.est["nu"]), pstd(crsp, CRSP.est["mu"], CRSP.est["sigma"], CRSP.est["nu"])) A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 29

30 ## Are the marginal distribution uniformly distributed? > h.n1 <- length(ibm)/10 > h.t <- h.n1 + 2*c(1,-1)*sqrt(h.n1) ## "confidence band" for height ## of bars in histogram > hist(ibm, col=gray(0.9)) > hist(crsp, col=gray(0.9)) > hist(ud[,1], col=gray(0.9)) > abline(h=h.t, col="gray") > hist(ud[,2], col=gray(0.9)) > abline(h=h.t, col="gray") A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 30

31 ## Fitting t copula in several steps ## from Kendall s tau to an estimation of Omega > (rhotau <- cor(ibm, CRSP, method="kendall")) [1] > (omega <- sin(pi/2*rhotau)) [1] ## Define the t-copula using Omega as correlation parameter > require(copula) > tc2 <-tcopula(omega, dim=2) ## fit by "maximum pseudo-likelihood" > (UD.tc2 <- fitcopula(tc2, data=ud, method="mpl",start=c(omega,8), + optim.method="l-bfgs-b", lower=c(0.1, 5.5), upper=c(0.7, 15))) fitcopula() estimation based on 'maximum pseudo-likelihood' and a sample of size Estimate Std. Error z value Pr(> z ) rho <2e-16 *** df NA NA NA --The maximized loglikelihood is Optimization converged A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 31

32 ## Fitting Gumbel, Frank and Clayton copulas > (UD.gc2 <- fitcopula(copula=gumbelcopula(3,dim=2), data=ud, + method="mpl", optim.method="bfgs")) fitcopula() estimation based on 'maximum pseudo-likelihood' and a sample of size Estimate Std. Error z value Pr(> z ) param <2e-16 *** --The maximized loglikelihood is Optimization converged ## Fitting Frank and Clayton copulas without R output (UD.fc2 <- fitcopula(copula=frankcopula(3,dim=2), data=ud, + method="mpl", optim.method="bfgs")) (UD.cc2 <- fitcopula(copula=claytoncopula(3,dim=2), data=ud, + method="mpl", optim.method="bfgs")) A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 32

33 ## Compare the empirical copula with the estimated ones ## using simulations > n <- nrow(ud) ## define the 4 copulas > ht <- tcopula(param=ud.tc2@estimate[1], df=round(ud.tc2@estimate[2])) > hg <- gumbelcopula(ud.gc2@estimate, dim=2) > hf <- frankcopula(ud.fc2@estimate, dim=2) > hc <- claytoncopula(ud.cc2@estimate, dim=2) > par(mfrow=c(2,3)) ## display data > plot(ud, main="data") ## simulate from the fitted copulas > set.seed(4711) > htr <- rcopula(n, ht); > hfr <- rcopula(n, hf); hgr <- rcopula(n, hg) hcr <- rcopula(n, hc) ## display simulated data > h.pplot <- function(x, main=""){ plot(x, main=main, xlab=expression(u[1]),ylab=expression(u[2]), col=rgb(0,0,1, alpha=0.2), pch=16) } > > > > h.pplot(htr, h.pplot(hgr, h.pplot(hfr, h.pplot(hcr, main="from main="from main="from main="from t copula") Gumbel copula") Frank copula ) Clayton copula") A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 33

34 Which simulated copula is most similar to the data? A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 34

35 u1 <- UD[,1]; u2 <- UD[,2] Udex <- (1:n)/(n+1) ## h.l <- c(0.02, 0.05, 0.1, 0.2, 0.4, 0.6, 0.8, 0.9) ## contour levels ## The function 'C.n()' from package copula computes the empirical copula Cn <- C.n(u=cbind(rep(Udex,n), rep(udex,each=n)), U=UD, offset=0,method="c") ## prepare the contours of the empirical copula: EmpCop <- expression(contour(udex, Udex, matrix(cn,n,n), col=2, add=t, levels=h.l)) par(mfrow=c(2,3), las=1, mar=c(3.5,4,2,1), cex.lab=1.2, mgp=c(2.2,0.8,0)) ## "raw" data plot(u1, u2, main="uniform...", xlab=expression(hat(u)[1]), ylab = expression(hat(u)[2])) ## t contour(tcopula(param=ud.tc2@estimate[1], dim=2, df=round(ud.tc2@estimate[2])), pcopula, main=expression(hat(c)[t]), levels=h.l, xlab=...) eval(empcop) ## Frank contour(frankcopula(param= UD.fc2@estimate[1], dim=2), pcopula, main=expression(hat(c)[fr]), levels=h.l, xlab=...) eval(empcop) ## Clayton contour(claytoncopula(param=ud.cc2@estimate[1], dim = 2), pcopula, main=expression(hat(c)[cl]), levels=h.l, xlab=...) eval(empcop) ## Gumbel contour(claytoncopula(param=ud.gc2@estimate[1], dim = 2), pcopula, main = expression(hat(c)[gu]), levels=h.l, xlab=...) eval(empcop) A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 35

36 A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 36

37 Assess the fit by AIC Akaike s information criterion AIC = -2log-likelihood + 2p ## with R > h.aic <- function(obj){ + np <- length(obj@estimate) + h <- obj@loglik + c(loglik=h, AIC=-2*h+2*np) } > rbind(h.aic(ud.tc2), h.aic(ud.fc2), h.aic(ud.gc2), h.aic(ud.cc2)) loglik AIC [1,] [2,] [3,] [4,] ## According to the AIC the t copula fits the data best A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 37

38 8.7* Vine Copula There is a wide range of parametric copula families (Gauss, t, Frank, Clayton,...) But: Standard multivariate copulas can become inflexible in high dimensions. do not allow for different dependency structures between pairs of variables. Way out: E.g., Vine copulas for higher-dimensional data Vine Copulas: Copulas The dependency structure is determined by bivariate copulas and a nested set of trees. Example in d=3 dimensions: One possible decomposition of f(x1,x2,x3) is: Since We obtain A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 38

39 The decomposition is not unique A graphical strucure called regular vine structure has been introduced to help organize them: See also R Package VineCopula more research is needed, particularly towards application A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 39

40 Take Home Message Lecture 5 Copulas are a general concept to model dependencies between random variables A copula is a multivariate cumulative distribution function (CDF) whose univariate marginal distributions are all uniform (0,1) To use copulas to model multivariate dependencies, we need parametric families of copulas Gaussian copula, t-copula, Archimedean copulas (e.g., Frank, Gumbel and Clayton copulas) In finance, the feature of modelling tail dependence is an advantageous characteristic of copulas t-copula, Clayton copula, Gumbel copula Practically, use the introduced copulas mainly to model 2 dimensional r.v. vine copulas enables a flexible modelling of the dependence structure for portfolios of large dimensions A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 40

41 Lecture 5 in the books: Chapter 8 Copulas Sections marked by * are not examined A. Ruckstuhl -- WBL 2017, Lecture 5 of SAoFD -- Page 41

8 Copulas. 8.1 Introduction

8 Copulas. 8.1 Introduction 8 Copulas 8.1 Introduction Copulas are a popular method for modeling multivariate distributions. A copula models the dependence and only the dependence between the variates in a multivariate distribution

More information

Financial Econometrics and Volatility Models Copulas

Financial Econometrics and Volatility Models Copulas Financial Econometrics and Volatility Models Copulas Eric Zivot Updated: May 10, 2010 Reading MFTS, chapter 19 FMUND, chapters 6 and 7 Introduction Capturing co-movement between financial asset returns

More information

Dependence. Practitioner Course: Portfolio Optimization. John Dodson. September 10, Dependence. John Dodson. Outline.

Dependence. Practitioner Course: Portfolio Optimization. John Dodson. September 10, Dependence. John Dodson. Outline. Practitioner Course: Portfolio Optimization September 10, 2008 Before we define dependence, it is useful to define Random variables X and Y are independent iff For all x, y. In particular, F (X,Y ) (x,

More information

Modelling Dependence with Copulas and Applications to Risk Management. Filip Lindskog, RiskLab, ETH Zürich

Modelling Dependence with Copulas and Applications to Risk Management. Filip Lindskog, RiskLab, ETH Zürich Modelling Dependence with Copulas and Applications to Risk Management Filip Lindskog, RiskLab, ETH Zürich 02-07-2000 Home page: http://www.math.ethz.ch/ lindskog E-mail: lindskog@math.ethz.ch RiskLab:

More information

Dependence. MFM Practitioner Module: Risk & Asset Allocation. John Dodson. September 11, Dependence. John Dodson. Outline.

Dependence. MFM Practitioner Module: Risk & Asset Allocation. John Dodson. September 11, Dependence. John Dodson. Outline. MFM Practitioner Module: Risk & Asset Allocation September 11, 2013 Before we define dependence, it is useful to define Random variables X and Y are independent iff For all x, y. In particular, F (X,Y

More information

Modelling Dependent Credit Risks

Modelling Dependent Credit Risks Modelling Dependent Credit Risks Filip Lindskog, RiskLab, ETH Zürich 30 November 2000 Home page:http://www.math.ethz.ch/ lindskog E-mail:lindskog@math.ethz.ch RiskLab:http://www.risklab.ch Modelling Dependent

More information

First steps of multivariate data analysis

First steps of multivariate data analysis First steps of multivariate data analysis November 28, 2016 Let s Have Some Coffee We reproduce the coffee example from Carmona, page 60 ff. This vignette is the first excursion away from univariate data.

More information

A simple graphical method to explore tail-dependence in stock-return pairs

A simple graphical method to explore tail-dependence in stock-return pairs A simple graphical method to explore tail-dependence in stock-return pairs Klaus Abberger, University of Konstanz, Germany Abstract: For a bivariate data set the dependence structure can not only be measured

More information

Copulas. Mathematisches Seminar (Prof. Dr. D. Filipovic) Di Uhr in E

Copulas. Mathematisches Seminar (Prof. Dr. D. Filipovic) Di Uhr in E Copulas Mathematisches Seminar (Prof. Dr. D. Filipovic) Di. 14-16 Uhr in E41 A Short Introduction 1 0.8 0.6 0.4 0.2 0 0 0.2 0.4 0.6 0.8 1 The above picture shows a scatterplot (500 points) from a pair

More information

Multivariate Distribution Models

Multivariate Distribution Models Multivariate Distribution Models Model Description While the probability distribution for an individual random variable is called marginal, the probability distribution for multiple random variables is

More information

Lecture Quantitative Finance Spring Term 2015

Lecture Quantitative Finance Spring Term 2015 on bivariate Lecture Quantitative Finance Spring Term 2015 Prof. Dr. Erich Walter Farkas Lecture 07: April 2, 2015 1 / 54 Outline on bivariate 1 2 bivariate 3 Distribution 4 5 6 7 8 Comments and conclusions

More information

7 Multivariate Statistical Models

7 Multivariate Statistical Models 7 Multivariate Statistical Models 7.1 Introduction Often we are not interested merely in a single random variable but rather in the joint behavior of several random variables, for example, returns on several

More information

Multivariate Non-Normally Distributed Random Variables

Multivariate Non-Normally Distributed Random Variables Multivariate Non-Normally Distributed Random Variables An Introduction to the Copula Approach Workgroup seminar on climate dynamics Meteorological Institute at the University of Bonn 18 January 2008, Bonn

More information

Modelling and Estimation of Stochastic Dependence

Modelling and Estimation of Stochastic Dependence Modelling and Estimation of Stochastic Dependence Uwe Schmock Based on joint work with Dr. Barbara Dengler Financial and Actuarial Mathematics and Christian Doppler Laboratory for Portfolio Risk Management

More information

Multivariate Distributions

Multivariate Distributions IEOR E4602: Quantitative Risk Management Spring 2016 c 2016 by Martin Haugh Multivariate Distributions We will study multivariate distributions in these notes, focusing 1 in particular on multivariate

More information

The Instability of Correlations: Measurement and the Implications for Market Risk

The Instability of Correlations: Measurement and the Implications for Market Risk The Instability of Correlations: Measurement and the Implications for Market Risk Prof. Massimo Guidolin 20254 Advanced Quantitative Methods for Asset Pricing and Structuring Winter/Spring 2018 Threshold

More information

GENERAL MULTIVARIATE DEPENDENCE USING ASSOCIATED COPULAS

GENERAL MULTIVARIATE DEPENDENCE USING ASSOCIATED COPULAS REVSTAT Statistical Journal Volume 14, Number 1, February 2016, 1 28 GENERAL MULTIVARIATE DEPENDENCE USING ASSOCIATED COPULAS Author: Yuri Salazar Flores Centre for Financial Risk, Macquarie University,

More information

Copula Regression RAHUL A. PARSA DRAKE UNIVERSITY & STUART A. KLUGMAN SOCIETY OF ACTUARIES CASUALTY ACTUARIAL SOCIETY MAY 18,2011

Copula Regression RAHUL A. PARSA DRAKE UNIVERSITY & STUART A. KLUGMAN SOCIETY OF ACTUARIES CASUALTY ACTUARIAL SOCIETY MAY 18,2011 Copula Regression RAHUL A. PARSA DRAKE UNIVERSITY & STUART A. KLUGMAN SOCIETY OF ACTUARIES CASUALTY ACTUARIAL SOCIETY MAY 18,2011 Outline Ordinary Least Squares (OLS) Regression Generalized Linear Models

More information

EVANESCE Implementation in S-PLUS FinMetrics Module. July 2, Insightful Corp

EVANESCE Implementation in S-PLUS FinMetrics Module. July 2, Insightful Corp EVANESCE Implementation in S-PLUS FinMetrics Module July 2, 2002 Insightful Corp The Extreme Value Analysis Employing Statistical Copula Estimation (EVANESCE) library for S-PLUS FinMetrics module provides

More information

Copulas and Measures of Dependence

Copulas and Measures of Dependence 1 Copulas and Measures of Dependence Uttara Naik-Nimbalkar December 28, 2014 Measures for determining the relationship between two variables: the Pearson s correlation coefficient, Kendalls tau and Spearmans

More information

Simulation of Tail Dependence in Cot-copula

Simulation of Tail Dependence in Cot-copula Int Statistical Inst: Proc 58th World Statistical Congress, 0, Dublin (Session CPS08) p477 Simulation of Tail Dependence in Cot-copula Pirmoradian, Azam Institute of Mathematical Sciences, Faculty of Science,

More information

Construction and estimation of high dimensional copulas

Construction and estimation of high dimensional copulas Construction and estimation of high dimensional copulas Gildas Mazo PhD work supervised by S. Girard and F. Forbes Mistis, Inria and laboratoire Jean Kuntzmann, Grenoble, France Séminaire Statistiques,

More information

Introduction to Dependence Modelling

Introduction to Dependence Modelling Introduction to Dependence Modelling Carole Bernard Berlin, May 2015. 1 Outline Modeling Dependence Part 1: Introduction 1 General concepts on dependence. 2 in 2 or N 3 dimensions. 3 Minimizing the expectation

More information

Gaussian Process Vine Copulas for Multivariate Dependence

Gaussian Process Vine Copulas for Multivariate Dependence Gaussian Process Vine Copulas for Multivariate Dependence José Miguel Hernández-Lobato 1,2 joint work with David López-Paz 2,3 and Zoubin Ghahramani 1 1 Department of Engineering, Cambridge University,

More information

Gaussian Slug Simple Nonlinearity Enhancement to the 1-Factor and Gaussian Copula Models in Finance, with Parametric Estimation and Goodness-of-Fit

Gaussian Slug Simple Nonlinearity Enhancement to the 1-Factor and Gaussian Copula Models in Finance, with Parametric Estimation and Goodness-of-Fit Gaussian Slug Simple Nonlinearity Enhancement to the 1-Factor and Gaussian Copula Models in Finance, with Parametric Estimation and Goodness-of-Fit Tests on US and Thai Equity Data 22 nd Australasian Finance

More information

A measure of radial asymmetry for bivariate copulas based on Sobolev norm

A measure of radial asymmetry for bivariate copulas based on Sobolev norm A measure of radial asymmetry for bivariate copulas based on Sobolev norm Ahmad Alikhani-Vafa Ali Dolati Abstract The modified Sobolev norm is used to construct an index for measuring the degree of radial

More information

How to select a good vine

How to select a good vine Universitetet i Oslo ingrihaf@math.uio.no International FocuStat Workshop on Focused Information Criteria and Related Themes, May 9-11, 2016 Copulae Regular vines Model selection and reduction Limitations

More information

A Brief Introduction to Copulas

A Brief Introduction to Copulas A Brief Introduction to Copulas Speaker: Hua, Lei February 24, 2009 Department of Statistics University of British Columbia Outline Introduction Definition Properties Archimedean Copulas Constructing Copulas

More information

When is a copula constant? A test for changing relationships

When is a copula constant? A test for changing relationships When is a copula constant? A test for changing relationships Fabio Busetti and Andrew Harvey Bank of Italy and University of Cambridge November 2007 usetti and Harvey (Bank of Italy and University of Cambridge)

More information

Clearly, if F is strictly increasing it has a single quasi-inverse, which equals the (ordinary) inverse function F 1 (or, sometimes, F 1 ).

Clearly, if F is strictly increasing it has a single quasi-inverse, which equals the (ordinary) inverse function F 1 (or, sometimes, F 1 ). APPENDIX A SIMLATION OF COPLAS Copulas have primary and direct applications in the simulation of dependent variables. We now present general procedures to simulate bivariate, as well as multivariate, dependent

More information

Bivariate Rainfall and Runoff Analysis Using Entropy and Copula Theories

Bivariate Rainfall and Runoff Analysis Using Entropy and Copula Theories Entropy 2012, 14, 1784-1812; doi:10.3390/e14091784 Article OPEN ACCESS entropy ISSN 1099-4300 www.mdpi.com/journal/entropy Bivariate Rainfall and Runoff Analysis Using Entropy and Copula Theories Lan Zhang

More information

Robustness of a semiparametric estimator of a copula

Robustness of a semiparametric estimator of a copula Robustness of a semiparametric estimator of a copula Gunky Kim a, Mervyn J. Silvapulle b and Paramsothy Silvapulle c a Department of Econometrics and Business Statistics, Monash University, c Caulfield

More information

Contents 1. Coping with Copulas. Thorsten Schmidt 1. Department of Mathematics, University of Leipzig Dec 2006

Contents 1. Coping with Copulas. Thorsten Schmidt 1. Department of Mathematics, University of Leipzig Dec 2006 Contents 1 Coping with Copulas Thorsten Schmidt 1 Department of Mathematics, University of Leipzig Dec 2006 Forthcoming in Risk Books Copulas - From Theory to Applications in Finance Contents 1 Introdcution

More information

Non-parametric Estimation of Elliptical Copulae With Application to Credit Risk

Non-parametric Estimation of Elliptical Copulae With Application to Credit Risk Non-parametric Estimation of Elliptical Copulae With Application to Credit Risk Krassimir Kostadinov Abstract This paper develops a method for statistical estimation of the dependence structure of financial

More information

On the Estimation and Application of Max-Stable Processes

On the Estimation and Application of Max-Stable Processes On the Estimation and Application of Max-Stable Processes Zhengjun Zhang Department of Statistics University of Wisconsin Madison, WI 53706, USA Co-author: Richard Smith EVA 2009, Fort Collins, CO Z. Zhang

More information

Copula-based top-down approaches in financial risk aggregation

Copula-based top-down approaches in financial risk aggregation Number 3 Working Paper Series by the University of Applied Sciences of bfi Vienna Copula-based top-down approaches in financial risk aggregation December 6 Christian Cech University of Applied Sciences

More information

Copula modeling for discrete data

Copula modeling for discrete data Copula modeling for discrete data Christian Genest & Johanna G. Nešlehová in collaboration with Bruno Rémillard McGill University and HEC Montréal ROBUST, September 11, 2016 Main question Suppose (X 1,

More information

SYSM 6303: Quantitative Introduction to Risk and Uncertainty in Business Lecture 4: Fitting Data to Distributions

SYSM 6303: Quantitative Introduction to Risk and Uncertainty in Business Lecture 4: Fitting Data to Distributions SYSM 6303: Quantitative Introduction to Risk and Uncertainty in Business Lecture 4: Fitting Data to Distributions M. Vidyasagar Cecil & Ida Green Chair The University of Texas at Dallas Email: M.Vidyasagar@utdallas.edu

More information

X

X Correlation: Pitfalls and Alternatives Paul Embrechts, Alexander McNeil & Daniel Straumann Departement Mathematik, ETH Zentrum, CH-8092 Zürich Tel: +41 1 632 61 62, Fax: +41 1 632 15 23 embrechts/mcneil/strauman@math.ethz.ch

More information

Package CopulaRegression

Package CopulaRegression Type Package Package CopulaRegression Title Bivariate Copula Based Regression Models Version 0.1-5 Depends R (>= 2.11.0), MASS, VineCopula Date 2014-09-04 Author, Daniel Silvestrini February 19, 2015 Maintainer

More information

A copula goodness-of-t approach. conditional probability integral transform. Daniel Berg 1 Henrik Bakken 2

A copula goodness-of-t approach. conditional probability integral transform. Daniel Berg 1 Henrik Bakken 2 based on the conditional probability integral transform Daniel Berg 1 Henrik Bakken 2 1 Norwegian Computing Center (NR) & University of Oslo (UiO) 2 Norwegian University of Science and Technology (NTNU)

More information

Multivariate Statistics

Multivariate Statistics Multivariate Statistics Chapter 2: Multivariate distributions and inference Pedro Galeano Departamento de Estadística Universidad Carlos III de Madrid pedro.galeano@uc3m.es Course 2016/2017 Master in Mathematical

More information

Copulas. MOU Lili. December, 2014

Copulas. MOU Lili. December, 2014 Copulas MOU Lili December, 2014 Outline Preliminary Introduction Formal Definition Copula Functions Estimating the Parameters Example Conclusion and Discussion Preliminary MOU Lili SEKE Team 3/30 Probability

More information

VaR vs. Expected Shortfall

VaR vs. Expected Shortfall VaR vs. Expected Shortfall Risk Measures under Solvency II Dietmar Pfeifer (2004) Risk measures and premium principles a comparison VaR vs. Expected Shortfall Dependence and its implications for risk measures

More information

Semi-parametric predictive inference for bivariate data using copulas

Semi-parametric predictive inference for bivariate data using copulas Semi-parametric predictive inference for bivariate data using copulas Tahani Coolen-Maturi a, Frank P.A. Coolen b,, Noryanti Muhammad b a Durham University Business School, Durham University, Durham, DH1

More information

A New Generalized Gumbel Copula for Multivariate Distributions

A New Generalized Gumbel Copula for Multivariate Distributions A New Generalized Gumbel Copula for Multivariate Distributions Chandra R. Bhat* The University of Texas at Austin Department of Civil, Architectural & Environmental Engineering University Station, C76,

More information

CONTAGION VERSUS FLIGHT TO QUALITY IN FINANCIAL MARKETS

CONTAGION VERSUS FLIGHT TO QUALITY IN FINANCIAL MARKETS EVA IV, CONTAGION VERSUS FLIGHT TO QUALITY IN FINANCIAL MARKETS Jose Olmo Department of Economics City University, London (joint work with Jesús Gonzalo, Universidad Carlos III de Madrid) 4th Conference

More information

Copulas and dependence measurement

Copulas and dependence measurement Copulas and dependence measurement Thorsten Schmidt. Chemnitz University of Technology, Mathematical Institute, Reichenhainer Str. 41, Chemnitz. thorsten.schmidt@mathematik.tu-chemnitz.de Keywords: copulas,

More information

Statistical analysis of empirical pairwise copulas for the S&P 500 stocks

Statistical analysis of empirical pairwise copulas for the S&P 500 stocks Statistical analysis of empirical pairwise copulas for the S&P 500 stocks Richard Koivusalo Supervisor KTH : Tatjana Pavlenko July 2012 Abstract It is of great importance to find an analytical copula that

More information

Vine Copulas. Spatial Copula Workshop 2014 September 22, Institute for Geoinformatics University of Münster.

Vine Copulas. Spatial Copula Workshop 2014 September 22, Institute for Geoinformatics University of Münster. Spatial Workshop 2014 September 22, 2014 Institute for Geoinformatics University of Münster http://ifgi.uni-muenster.de/graeler 1 spatio-temporal data Typically, spatio-temporal data is given at a set

More information

Vine copulas with asymmetric tail dependence and applications to financial return data 1. Abstract

Vine copulas with asymmetric tail dependence and applications to financial return data 1. Abstract *Manuscript Vine copulas with asymmetric tail dependence and applications to financial return data 1 Aristidis K. Nikoloulopoulos 2, Harry Joe 3 and Haijun Li 4 Abstract In Aas et al. (2009) and Aas and

More information

Bivariate Paired Numerical Data

Bivariate Paired Numerical Data Bivariate Paired Numerical Data Pearson s correlation, Spearman s ρ and Kendall s τ, tests of independence University of California, San Diego Instructor: Ery Arias-Castro http://math.ucsd.edu/~eariasca/teaching.html

More information

On the Systemic Nature of Weather Risk

On the Systemic Nature of Weather Risk Martin Odening 1 Ostap Okhrin 2 Wei Xu 1 Department of Agricultural Economics 1 Ladislaus von Bortkiewicz Chair of Statistics C.A.S.E. Center for Applied Statistics and Economics 2 Humboldt Universität

More information

Conditional Least Squares and Copulae in Claims Reserving for a Single Line of Business

Conditional Least Squares and Copulae in Claims Reserving for a Single Line of Business Conditional Least Squares and Copulae in Claims Reserving for a Single Line of Business Michal Pešta Charles University in Prague Faculty of Mathematics and Physics Ostap Okhrin Dresden University of Technology

More information

Simulating Exchangeable Multivariate Archimedean Copulas and its Applications. Authors: Florence Wu Emiliano A. Valdez Michael Sherris

Simulating Exchangeable Multivariate Archimedean Copulas and its Applications. Authors: Florence Wu Emiliano A. Valdez Michael Sherris Simulating Exchangeable Multivariate Archimedean Copulas and its Applications Authors: Florence Wu Emiliano A. Valdez Michael Sherris Literatures Frees and Valdez (1999) Understanding Relationships Using

More information

Pair-copula constructions of multiple dependence

Pair-copula constructions of multiple dependence Pair-copula constructions of multiple dependence 3 4 5 3 34 45 T 3 34 45 3 4 3 35 4 T 3 4 3 35 4 4 3 5 34 T 3 4 3 5 34 5 34 T 4 Note no SAMBA/4/06 Authors Kjersti Aas Claudia Czado Arnoldo Frigessi Henrik

More information

Efficient estimation of a semiparametric dynamic copula model

Efficient estimation of a semiparametric dynamic copula model Efficient estimation of a semiparametric dynamic copula model Christian Hafner Olga Reznikova Institute of Statistics Université catholique de Louvain Louvain-la-Neuve, Blgium 30 January 2009 Young Researchers

More information

Trivariate copulas for characterisation of droughts

Trivariate copulas for characterisation of droughts ANZIAM J. 49 (EMAC2007) pp.c306 C323, 2008 C306 Trivariate copulas for characterisation of droughts G. Wong 1 M. F. Lambert 2 A. V. Metcalfe 3 (Received 3 August 2007; revised 4 January 2008) Abstract

More information

Program and big picture Big data: can copula modelling be used for high dimensions, say

Program and big picture Big data: can copula modelling be used for high dimensions, say Conditional independence copula models with graphical representations Harry Joe (University of British Columbia) For multivariate Gaussian with a large number of variables, there are several approaches

More information

Time Varying Hierarchical Archimedean Copulae (HALOC)

Time Varying Hierarchical Archimedean Copulae (HALOC) Time Varying Hierarchical Archimedean Copulae () Wolfgang Härdle Ostap Okhrin Yarema Okhrin Ladislaus von Bortkiewicz Chair of Statistics C.A.S.E. Center for Applied Statistics and Economics Humboldt-Universität

More information

Non parametric estimation of Archimedean copulas and tail dependence. Paris, february 19, 2015.

Non parametric estimation of Archimedean copulas and tail dependence. Paris, february 19, 2015. Non parametric estimation of Archimedean copulas and tail dependence Elena Di Bernardino a and Didier Rullière b Paris, february 19, 2015. a CNAM, Paris, Département IMATH, b ISFA, Université Lyon 1, Laboratoire

More information

Nonparametric estimation of simplified vine copula models: comparison of methods

Nonparametric estimation of simplified vine copula models: comparison of methods Depend. Model. 17; 5:99 1 Research Article Special Issue: Salzburg Workshop on Dependence Models & Copulas Open Access Thomas Nagler*, Christian Schellhase, and Claudia Czado Nonparametric estimation of

More information

Probability Distribution And Density For Functional Random Variables

Probability Distribution And Density For Functional Random Variables Probability Distribution And Density For Functional Random Variables E. Cuvelier 1 M. Noirhomme-Fraiture 1 1 Institut d Informatique Facultés Universitaires Notre-Dame de la paix Namur CIL Research Contact

More information

Web-based Supplementary Material for A Two-Part Joint. Model for the Analysis of Survival and Longitudinal Binary. Data with excess Zeros

Web-based Supplementary Material for A Two-Part Joint. Model for the Analysis of Survival and Longitudinal Binary. Data with excess Zeros Web-based Supplementary Material for A Two-Part Joint Model for the Analysis of Survival and Longitudinal Binary Data with excess Zeros Dimitris Rizopoulos, 1 Geert Verbeke, 1 Emmanuel Lesaffre 1 and Yves

More information

Asymptotic behaviour of multivariate default probabilities and default correlations under stress

Asymptotic behaviour of multivariate default probabilities and default correlations under stress Asymptotic behaviour of multivariate default probabilities and default correlations under stress 7th General AMaMeF and Swissquote Conference EPFL, Lausanne Natalie Packham joint with Michael Kalkbrener

More information

Half-Day 1: Introduction to Robust Estimation Techniques

Half-Day 1: Introduction to Robust Estimation Techniques Zurich University of Applied Sciences School of Engineering IDP Institute of Data Analysis and Process Design Half-Day 1: Introduction to Robust Estimation Techniques Andreas Ruckstuhl Institut fr Datenanalyse

More information

Lecture 2: Univariate Time Series

Lecture 2: Univariate Time Series Lecture 2: Univariate Time Series Analysis: Conditional and Unconditional Densities, Stationarity, ARMA Processes Prof. Massimo Guidolin 20192 Financial Econometrics Spring/Winter 2017 Overview Motivation:

More information

Probability Distributions and Estimation of Ali-Mikhail-Haq Copula

Probability Distributions and Estimation of Ali-Mikhail-Haq Copula Applied Mathematical Sciences, Vol. 4, 2010, no. 14, 657-666 Probability Distributions and Estimation of Ali-Mikhail-Haq Copula Pranesh Kumar Mathematics Department University of Northern British Columbia

More information

Unit 14: Nonparametric Statistical Methods

Unit 14: Nonparametric Statistical Methods Unit 14: Nonparametric Statistical Methods Statistics 571: Statistical Methods Ramón V. León 8/8/2003 Unit 14 - Stat 571 - Ramón V. León 1 Introductory Remarks Most methods studied so far have been based

More information

On the Conditional Value at Risk (CoVaR) from the copula perspective

On the Conditional Value at Risk (CoVaR) from the copula perspective On the Conditional Value at Risk (CoVaR) from the copula perspective Piotr Jaworski Institute of Mathematics, Warsaw University, Poland email: P.Jaworski@mimuw.edu.pl 1 Overview 1. Basics about VaR, CoVaR

More information

Copulas, Higher-Moments and Tail Risks

Copulas, Higher-Moments and Tail Risks Copulas, Higher-Moments and Tail Risks ETH-Zurich Chair of Entrepreneurial Risks Department of Management, Technology and Economics (D-MTEC) Zurich, Switzerland http://www.mtec.ethz.ch/ Optimal orthogonal

More information

Correlation & Dependency Structures

Correlation & Dependency Structures Correlation & Dependency Structures GIRO - October 1999 Andrzej Czernuszewicz Dimitris Papachristou Why are we interested in correlation/dependency? Risk management Portfolio management Reinsurance purchase

More information

Ensemble Copula Coupling (ECC)

Ensemble Copula Coupling (ECC) Ensemble Copula Coupling (ECC) Tilmann Gneiting Institut für Angewandte Mathematik Universität Heidelberg BfG Kolloquium, Koblenz 24. September 2013 Statistical Postprocessing of Ensemble Forecasts: EMOS/NR

More information

Truncation of vine copulas using fit indices

Truncation of vine copulas using fit indices Truncation of vine copulas using fit indices Eike C. Brechmann Harry Joe February 2, 2015 Abstract Vine copulas are flexible multivariate dependence models, which are built up from a set of bivariate copulas

More information

EXTREMAL DEPENDENCE OF MULTIVARIATE DISTRIBUTIONS AND ITS APPLICATIONS YANNAN SUN

EXTREMAL DEPENDENCE OF MULTIVARIATE DISTRIBUTIONS AND ITS APPLICATIONS YANNAN SUN EXTREMAL DEPENDENCE OF MULTIVARIATE DISTRIBUTIONS AND ITS APPLICATIONS By YANNAN SUN A dissertation submitted in partial fulfillment of the requirements for the degree of DOCTOR OF PHILOSOPHY WASHINGTON

More information

Songklanakarin Journal of Science and Technology SJST R1 Sukparungsee

Songklanakarin Journal of Science and Technology SJST R1 Sukparungsee Songklanakarin Journal of Science and Technology SJST-0-0.R Sukparungsee Bivariate copulas on the exponentially weighted moving average control chart Journal: Songklanakarin Journal of Science and Technology

More information

Bayesian Inference for Pair-copula Constructions of Multiple Dependence

Bayesian Inference for Pair-copula Constructions of Multiple Dependence Bayesian Inference for Pair-copula Constructions of Multiple Dependence Claudia Czado and Aleksey Min Technische Universität München cczado@ma.tum.de, aleksmin@ma.tum.de December 7, 2007 Overview 1 Introduction

More information

Assessing the VaR of a portfolio using D-vine copula based multivariate GARCH models

Assessing the VaR of a portfolio using D-vine copula based multivariate GARCH models Assessing the VaR of a portfolio using D-vine copula based multivariate GARCH models Mathias Hofmann a,, Claudia Czado b a Technische Universität München Zentrum Mathematik Lehrstuhl für Mathematische

More information

1 Description of variables

1 Description of variables 1 Description of variables We have three possible instruments/state variables: dividend yield d t+1, default spread y t+1, and realized market volatility v t+1 d t is the continuously compounded 12 month

More information

Estimation of multivariate critical layers: Applications to rainfall data

Estimation of multivariate critical layers: Applications to rainfall data Elena Di Bernardino, ICRA 6 / RISK 2015 () Estimation of Multivariate critical layers Barcelona, May 26-29, 2015 Estimation of multivariate critical layers: Applications to rainfall data Elena Di Bernardino,

More information

Lecture 03 Positive Semidefinite (PSD) and Positive Definite (PD) Matrices and their Properties

Lecture 03 Positive Semidefinite (PSD) and Positive Definite (PD) Matrices and their Properties Applied Optimization for Wireless, Machine Learning, Big Data Prof. Aditya K. Jagannatham Department of Electrical Engineering Indian Institute of Technology, Kanpur Lecture 03 Positive Semidefinite (PSD)

More information

Identification of marginal and joint CDFs using Bayesian method for RBDO

Identification of marginal and joint CDFs using Bayesian method for RBDO Struct Multidisc Optim (2010) 40:35 51 DOI 10.1007/s00158-009-0385-1 RESEARCH PAPER Identification of marginal and joint CDFs using Bayesian method for RBDO Yoojeong Noh K. K. Choi Ikjin Lee Received:

More information

Examples of vines and vine copulas Harry Joe July 24/31, 2015; Graphical models reading group

Examples of vines and vine copulas Harry Joe July 24/31, 2015; Graphical models reading group Examples of vines and vine copulas Harry Joe July 4/31, 015; Graphical models reading group Outline Examples with correlation matrices Example showing continuous variables and non-gaussian dependence Example

More information

Generalized Autoregressive Score Models

Generalized Autoregressive Score Models Generalized Autoregressive Score Models by: Drew Creal, Siem Jan Koopman, André Lucas To capture the dynamic behavior of univariate and multivariate time series processes, we can allow parameters to be

More information

the long tau-path for detecting monotone association in an unspecified subpopulation

the long tau-path for detecting monotone association in an unspecified subpopulation the long tau-path for detecting monotone association in an unspecified subpopulation Joe Verducci Current Challenges in Statistical Learning Workshop Banff International Research Station Tuesday, December

More information

Reducing Model Risk With Goodness-of-fit Victory Idowu London School of Economics

Reducing Model Risk With Goodness-of-fit Victory Idowu London School of Economics Reducing Model Risk With Goodness-of-fit Victory Idowu London School of Economics Agenda I. An overview of Copula Theory II. Copulas and Model Risk III. Goodness-of-fit methods for copulas IV. Presentation

More information

Elements of Financial Engineering Course

Elements of Financial Engineering Course Elements of Financial Engineering Course Baruch-NSD Summer Camp 0 Lecture Tai-Ho Wang Agenda Methods of simulation: inverse transformation method, acceptance-rejection method Variance reduction techniques

More information

Overview of Extreme Value Theory. Dr. Sawsan Hilal space

Overview of Extreme Value Theory. Dr. Sawsan Hilal space Overview of Extreme Value Theory Dr. Sawsan Hilal space Maths Department - University of Bahrain space November 2010 Outline Part-1: Univariate Extremes Motivation Threshold Exceedances Part-2: Bivariate

More information

Forecasting time series with multivariate copulas

Forecasting time series with multivariate copulas Depend. Model. 2015; 3:59 82 Research Article Open Access Clarence Simard* and Bruno Rémillard Forecasting time series with multivariate copulas DOI 10.1515/demo-2015-0005 5 Received august 17, 2014; accepted

More information

Review (probability, linear algebra) CE-717 : Machine Learning Sharif University of Technology

Review (probability, linear algebra) CE-717 : Machine Learning Sharif University of Technology Review (probability, linear algebra) CE-717 : Machine Learning Sharif University of Technology M. Soleymani Fall 2012 Some slides have been adopted from Prof. H.R. Rabiee s and also Prof. R. Gutierrez-Osuna

More information

AR, MA and ARMA models

AR, MA and ARMA models AR, MA and AR by Hedibert Lopes P Based on Tsay s Analysis of Financial Time Series (3rd edition) P 1 Stationarity 2 3 4 5 6 7 P 8 9 10 11 Outline P Linear Time Series Analysis and Its Applications For

More information

Estimation of Copula Models with Discrete Margins (via Bayesian Data Augmentation) Michael S. Smith

Estimation of Copula Models with Discrete Margins (via Bayesian Data Augmentation) Michael S. Smith Estimation of Copula Models with Discrete Margins (via Bayesian Data Augmentation) Michael S. Smith Melbourne Business School, University of Melbourne (Joint with Mohamad Khaled, University of Queensland)

More information

Bayesian Model Selection of Regular Vine Copulas

Bayesian Model Selection of Regular Vine Copulas Bayesian Model Selection of Regular Vine Copulas Lutz F. Gruber Claudia Czado Abstract Regular vine copulas are a novel and very flexible class of dependence models. This paper presents a reversible jump

More information

Outline. Frailty modelling of Multivariate Survival Data. Clustered survival data. Clustered survival data

Outline. Frailty modelling of Multivariate Survival Data. Clustered survival data. Clustered survival data Outline Frailty modelling of Multivariate Survival Data Thomas Scheike ts@biostat.ku.dk Department of Biostatistics University of Copenhagen Marginal versus Frailty models. Two-stage frailty models: copula

More information

Correlation: Copulas and Conditioning

Correlation: Copulas and Conditioning Correlation: Copulas and Conditioning This note reviews two methods of simulating correlated variates: copula methods and conditional distributions, and the relationships between them. Particular emphasis

More information

Extreme Value Analysis and Spatial Extremes

Extreme Value Analysis and Spatial Extremes Extreme Value Analysis and Department of Statistics Purdue University 11/07/2013 Outline Motivation 1 Motivation 2 Extreme Value Theorem and 3 Bayesian Hierarchical Models Copula Models Max-stable Models

More information

Gaussian Process Vine Copulas for Multivariate Dependence

Gaussian Process Vine Copulas for Multivariate Dependence Gaussian Process Vine Copulas for Multivariate Dependence José Miguel Hernández Lobato 1,2, David López Paz 3,2 and Zoubin Ghahramani 1 June 27, 2013 1 University of Cambridge 2 Equal Contributor 3 Ma-Planck-Institute

More information

Chapter 5 continued. Chapter 5 sections

Chapter 5 continued. Chapter 5 sections Chapter 5 sections Discrete univariate distributions: 5.2 Bernoulli and Binomial distributions Just skim 5.3 Hypergeometric distributions 5.4 Poisson distributions Just skim 5.5 Negative Binomial distributions

More information

Imputation Algorithm Using Copulas

Imputation Algorithm Using Copulas Metodološki zvezki, Vol. 3, No. 1, 2006, 109-120 Imputation Algorithm Using Copulas Ene Käärik 1 Abstract In this paper the author demonstrates how the copulas approach can be used to find algorithms for

More information

Marginal Specifications and a Gaussian Copula Estimation

Marginal Specifications and a Gaussian Copula Estimation Marginal Specifications and a Gaussian Copula Estimation Kazim Azam Abstract Multivariate analysis involving random variables of different type like count, continuous or mixture of both is frequently required

More information