Bayesian model selection for D-vine pair-copula constructions. (English. French summary) Zbl 1219.62048

Summary: In recent years analyses of dependence structures using copulas have become more popular than the standard correlation analysis. Starting from K. Aas et al. [Insur. Math. Econ. 44, No. 2, 182–198 (2009; Zbl 1165.60009)] regular vine pair-copula constructions (PCCs) are considered the most flexible class of multivariate copulas. PCCs are involved objects but (conditional) independence present in data can simplify and reduce them significantly. The authors detect (conditional) independence in a particular vine PCC model based on bivariate t copulas by deriving and implementing a reversible jump Markov chain Monte Carlo algorithm. However, the methodology is general and can be extended to any regular vine PCC and to all known bivariate copula families. The proposed approach considers model selection and estimation problems for PCCs simultaneously. The effectiveness of the developed algorithm is shown in simulations and its usefulness is illustrated in two real data applications.


62F15 Bayesian inference
62H20 Measures of association (correlation, canonical correlation, etc.)
62H05 Characterization and structure theory for multivariate probability distributions; copulas
65C40 Numerical analysis or methods applied to Markov chains


Zbl 1165.60009
Full Text: DOI


[1] Aas, Pair-copula constructions of multiple dependence, Insurance: Mathematics and Economomics 44 pp 182– (2009) · Zbl 1165.60009
[2] V. Arakelian P. Dellaportas 2010 Contagion determination via copula and volatility threshold models Quantitative Finance · Zbl 1241.91134
[3] Bedford, Probability density decomposition for conditionally dependent random variables modeled by vines, Annals of Mathematics and Artificial Intelligence 32 pp 245– (2001) · Zbl 1314.62040
[4] Bedford, Vines-A new graphical model for dependent random variables, Annals of Statistics 30 pp 1031– (2002) · Zbl 1101.62339
[5] Berg, Models for construction of multivariate dependence, European Journal of Finance 15 pp 639– (2009)
[6] Besag, Bayesian computation and stochastic systems, Statistical Science 10 pp 3– (1995) · Zbl 0955.62552
[7] Chan, Statistical inference for multivariate residual copula of GARCH models, Statistica Sinica 19 pp 53– (2009) · Zbl 1153.62068
[8] Chen, Estimation and model selection of semiparametric copula-based multivariate dynamic models under copula misspecification, Journal of Econometrics 135 pp 125– (2006) · Zbl 1418.62425
[9] Congdon, Bayesian model choice based on Monte Carlo estimates of posterior model probabilities, Computational Statistics & Data Analysis 50 pp 346– (2006) · Zbl 1330.62115
[10] C. Czado F. Gärtner A. Min 2010 Analysis of Australian Electricity Loads Using Joint Bayesian Inference of D-Vines With Autoregressive Margins Dependence Modelling: Handbook on Vine Copulae,
[11] Dalla Valle, Bayesian copulae distributions with application to operational risk management, Methodology and Computing in Applied Probability 11 pp 95– (2009) · Zbl 1293.62016
[12] Demarta, The t copula and related copulas, International Statistical Review 73 pp 111– (2005) · Zbl 1104.62060
[13] P. Embrechts A.J. McNeil D. Straumann 2002 Correlation and Dependance in Risk Management: Properties and Pitfalls Risk Management: Value at Risk and Beyond,
[14] P. Embrechts F. Lindskog A. J. McNeil 2003 Modelling Dependence With Copulas and Applications to Risk Management Handbook of Heavy Tailed Distributions in Finance,
[15] Fischer, An empirical analysis of multivariate copula models, Quantitative Finance 7 pp 839– (2009) · Zbl 1180.91314
[16] B. Flury H. Riedwyl 1988 ” Multivariate Statistics: A Practical Approach ,” Chapman & Hall, New York · Zbl 1081.62535
[17] Frahm, Elliptical copulas: Applicability and limitations, Statistics & Probability Letters 63 pp 275– (2003) · Zbl 1116.62352
[18] Frees, Understanding relationships using copulas, The North American Actuarial Journal 2 pp 1– (1998) · Zbl 1081.62564
[19] Genest, Everything you always wanted to know about copula modeling but were afraid to ask, Journal of Hydrologic Engineering 12 pp 347– (2007)
[20] Genest, A semiparametric estimation procedure of dependence parameters in multivariate families of distributions, Biometrika 82 pp 543– (1995) · Zbl 0831.62030
[21] C. Genest M. Gendron M. Bourdeau-Brien 2009 The advent of copulas in finance European Journal of Finance
[22] Green, Reversible jump Markov chain Monte Carlo computation and Bayesian model determination, Biometrika 82 pp 711– (1995) · Zbl 0861.62023
[23] Hastings, Monte Carlo sampling methods using Markov chains and their applications, Biometrika 57 pp 97– (1970) · Zbl 0219.65008
[24] Hobaek Haff, On the simplified pair-copula construction-Simply useful or too simplistic, Journal of Multivariate Analysis 101 pp 1296– (2010) · Zbl 1184.62079
[25] M. Hofmann C. Czado 2010 Assessing the VaR of a portfolio using D-vine copula based multivariate GARCH models Working Paper
[26] Huard, Bayesian copula selection, Computational Statistics & Data Analysis 51 pp 809– (2006) · Zbl 1157.62359
[27] H. Joe 1996 Families of m -Variate Distributions With Given Margins and m ( m -1)/2 Bivariate Dependence Parameters Distributions With Fixed Marginals and Related Topics
[28] H. Joe 1997 ” Multivariate Models and Dependence Concepts ,” Chapman & Hall, London · Zbl 0990.62517
[29] Joe, Asymptotic efficiency of the two stage estimation method for copula-based models, Journal of Multivariate Analysis 94 pp 401– (2005) · Zbl 1066.62061
[30] Kim, Comparison of semiparametric and parametric methods for estimating copulas, Computational Statistics & Data Analysis 51 pp 2836– (2007) · Zbl 1161.62364
[31] D. Kurowicka R. Cooke 2006 ” Uncertainty Analysis With High Dimensional Dependence Modelling ,” John Wiley & Sons, Chichester · Zbl 1096.62073
[32] Li, On default correlation: A copula function approach, Journal of Fixed Income 9 pp 43– (2000)
[33] J. Ma 2010 Bayesian inference for D-vine pair-copula constructions based on different bivariate families http://www-m4.ma.tum.de/Diplarb/diplomarbeiten.html
[34] McNeil, Multivariate Archimedean copulas, \(d-\)monotone functions and \(l_1\) norm symmetric distributions, Annals of Statistics 37 pp 3059– (2009) · Zbl 1173.62044
[35] Metropolis, Equations of state calculations by fast computing machines, Journal of Chemical Physics 21 pp 1087– (1953)
[36] Min, Bayesian inference for multivariate copulas using pair-copula constructions, Journal of Financial Econometrics 8 pp 511– (2010a)
[37] A. Min C. Czado 2010b SCOMDY models based on pair-copula constructions with application to exchange rates Working Paper
[38] Nelsen, An Introduction to Copulas (1999) · Zbl 0909.62052
[39] Patton, On the out-of-sample importance of skewness and asymmetric dependence for asset allocation, Journal of Financial Econometrics 2 pp 130– (2004)
[40] A. J. Patton 2009 Copula-Based Models for Financial Time Series Handbook of Financial Time Series, · Zbl 1178.91228
[41] Pitt, Efficient Bayesian inference for Gaussian copula regression models, Biometrika 93 pp 537– (2006) · Zbl 1108.62027
[42] Richardson, On Bayesian analysis of mixtures with an unknown number of components, Journal of the Royal Statistical Society Series B 59 pp 731– (1997) · Zbl 0891.62020
[43] Robert, Some difficulties with some posterior probability approximations, Bayesian Analysis 3 pp 427– (2008) · Zbl 1330.62149
[44] d. S. Silva, Copula, marginal distributions and model selection: A Bayesian note, Statistics and Computing 18 pp 313– (2008)
[45] Sklar, Fonctions de répartition à n dimensions et leurs marges, Publications de l’Institut de Statistique de l’Université de Paris 8 pp 229– (1959)
[46] -K. Song, Multivariate dispersion models generated from Gaussian copula, Scandinavian Journal of Statistics 27 pp 305– (2000) · Zbl 0955.62054
[47] G. U. Yule M. G. Kendall 1965 An Introduction to the Theory of Statistics · Zbl 0030.30705
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.