Selection strategies for regular vine copulae

Czado, Claudia; Jeske, Stephan; Hofmann, Mathias

Journal de la société française de statistique, Tome 154 (2013) no. 1, pp. 174-191.

Les grappes régulières de copules (« R-vines » en anglais) forment une famille flexible de copules de plus en plus fréquemment utilisée dans le domaine de la finance et de l’assurance. Dans un premier temps, nous présentons ces copules et nous discutons leur estimation. La classe des grappes régulières de copules étant très riche, il est crucial de disposer d’outils de sélection de modèles. Dans un deuxième temps, nous nous intéressons ainsi à un algorithme descendant de sélection de modèles récemment suggéré et nous en proposons une extension fondée sur des tests d’adéquation. L’utilisation de grappes régulières de copules et des algorithmes de sélection étudiés est enfin illustrée sur des données de concentrations chimiques.

Regular vine (R-vine) copulae are a very flexible class of multivariate copulae, which have received increasing interest in finance and insurance. We will introduce these copulae, discuss their scope and parameter estimation. Since the class of R-vines is huge, model class selection is vital. Recently a top down and a bottom up approach for model selection have been developed. We will discuss these approaches and introduce some useful extensions based on using $p$-values of goodness-of-fit tests as selection weights. The use of R-vine copulae will be illustrated for a data set involving log concentrations of chemicals in water samples. The performance of these selection procedures are investigated through simulation.

Keywords: copulae, regular vines, model selection
Mot clés : grappes régulières de copules, regular vines, sélection de modèles

[1] Aas, K.; Czado, C.; Frigessi, A.; Bakken, H. Pair-copula construction of multiple dependence, Insurance: Mathematics and Economics, Volume 44 (2009), pp. 182-198 | MR | Zbl

[2] Almeida, C.; Czado, C.; Manner, H. Modeling high dimensional time-varying dependence using D-vine SCAR models (2012) (Preprint) | MR

[3] Acar, E.F.; Genest, C.; Nes̆tlehová, J. Beyond simplified pair-copula constructions, Journal of Multivariate Analysis, Volume 110 (2012), pp. 74-90 | MR | Zbl

[4] Akaike, H. Information Theory and an Extension of the Maximum Likelihood Principle, Proceedings of the Second International Symposium on Information Theory (1973), pp. 267-281 | MR | Zbl

[5] Bedford, T.; Cooke, R. Probability density decomposition for conditionally dependent random variables modeled by vines, Annals of Mathematics and Artificial Intelligence, Volume 32 (2001), pp. 245-268 | MR | Zbl

[6] Bedford, T.; Cooke, R.M. Vines - a new graphical model for dependent random variables, Annals of Statistics, Volume 30 (2002) no. 4, pp. 1031-1068 | MR | Zbl

[7] Bernard, C.; Czado, C. Multivariate option pricing using copulae, Applied Stochastic Models in Business and Industry (2012), p. n/a-n/a | DOI | MR

[8] Brechmann, E.C.; Czado, C. COPAR - Multivariate Time Series Modeling Using the COPula AutoRegressive Model. (2012) (Preprint) | MR

[9] Brechmann, E.C.; Czado, C. Risk Management with High-Dimensional Vine Copulas: An Analysis of the Euro Stoxx 50 (2012) (Preprint) | MR

[10] Brechmann, E.C.; Czado, C.; Aas, K. Truncated Regular Vines in High Dimensions with Applications to Financial Data, Canadian Journal of Statistics, Volume 40 (2012) no. 1, pp. 68-85 | MR | Zbl

[11] Bauer, A.; Czado, C.; Klein, T. Pair-copula constructions for non-Gaussian DAG models, Canadian Journal of Statistics, Volume 40 (2012), pp. 86-109 | MR | Zbl

[12] Berg, D. Copula goodness-of-fit testing: an overview and power comparison, The European Journal of Finance, Volume 15 (2009) no. 7-8, pp. 675-701

[13] Ben Ghorbal, N.; Genest, C.; Nes̆tlehová, J. On the Ghoudi, Khoudraji and Rivest test for extreme-value dependence, Canadian Journal of Statistics, Volume 37 (2009), pp. 534-552 | MR | Zbl

[14] Brechmann, E.C. Truncated and simplified regular vines and their applications, Technische Universität München (2010) (Masters thesis)

[15] Baba, K.; Shibata, R.; Sibuya, M. Partial Correlation and Conditional Correlation as Measures of Conditional Independence, Australian and New Zealand Journal of Statistics, Volume 46(4) (2004), pp. 657-664 | MR | Zbl

[16] Chen, X.; Fan, Y. Estimation and model selection of semi-parametric copula based multivariate dynamic models under copula misspecification, Canadian Journal of Statistics (2006) | MR | Zbl

[17] Chollete, L.; Heinen, A.; Valdesogo, A. Modeling international financial returns with a multivariate regime switching copula (2008) (Preprint)

[18] Cook, R.D.; Johnson, M.E. A family of distributions for modeling nonelliptically symmetric multivariate data, Journal of the Royal Statistical Society, Series B, Volume 43 (1981), pp. 210-218 | MR | Zbl

[19] Cormen, T.H.; Leiserson, E.C.; Rivest, R.L.; Stein, C. Introduction to Algorithms, The MIT Press, 2009 | MR

[20] Czado, C.; Schepsmeier, U.; Min, A. Maximum likelihood estimation of mixed C-vine pair copula with application to exchange rates, Statistical Modelling, Volume 12 (2012), pp. 229-255 | MR | Zbl

[21] Dißmann, J.; Brechmann, E.C.; Czado, C.; Kurowicka, D. Selecting and estimating regular vine copulae and application to financial returns, Computational Statistics & Data Analysis, Volume 59 (2013), pp. 52-69 | MR | Zbl

[22] Frahm, G.; Junker, M.; Szimayer, A. Elliptical copulas: applicability and limitations, Statistics & Probability Letters, Volume 63 (2003) no. 3, pp. 275-286 | MR | Zbl

[23] Gruber, L.; Czado, C. Sequential Bayesian Model Selection of Regular Vine Copulas, Preprint (2013) | MR | Zbl

[24] Genest, C.; Ghoudi, K.; Rivest, L.-P. A semiparametric estimation procedure of dependence parameters in multivariate families of distributions, Biometrika, Volume 82 (1995), pp. 543-552 | MR | Zbl

[25] Genest, C.; Remillard, B. Validity of the parametric bootstrap for goodness of fit testing in semiparametric models, Annales de l’Institut Henri Pointcare: Probabilities et Statistiques, Volume 44 (2008), pp. 1096-1127 | Numdam | MR | Zbl

[26] Genest, C.; Remillard, B.; Beaudoin, D. Goodness-of-fit tests for copulas: A review and a power study, Insurance: Mathematics and Economics, Volume 44 (2009) no. 2, pp. 199-213 http://ideas.repec.org/a/eee/insuma/v44y2009i2p199-213.html | MR | Zbl

[27] Hobak Haff, I.; Aas, K.; Frigessi, A. On the simplified pair-copula construction - simply useful or too simplistic?, Journal of Multivariate Analysis, Volume 101 (2010), pp. 1296-1310 | MR | Zbl

[28] Hobak Haff, I Parameter estimation for pair-copula constructions, Bernoulli (in Press) (2012) | MR

[29] Joe, H. Families of m-variate distributions with given margins and m(m-1)/2 bivariate dependence parameters, Distributions with Fixed Marginals and Related Topics (L. Rüschendorf and B. Schweizer and M. D. Taylor, ed.) (1996) | MR

[30] Joe, H. Multivariate Models and Dependence Concepts, Chapman & Hall, London, 1997 | MR | Zbl

[31] Joe, H.; Xu, J. The estimation method of inference functions for margins of multivariate models, Technical Report 166, Department of Statistics, University of British Columbia (1996)

[32] Kurowicka, D.; Cooke, R. Uncertainty Analysis with High Dimensional Dependence Modelling, John Wiley & Sons, Ltd, 2008 | MR | Zbl

[33] Kurowicka, D.; Joe, H. Dependence Modeling: Vine Copula Handbook, World Scientific Publishing Co., Singapore, 2011 | MR

[34] Krupskii, P.; Joe, H. Factor copula models for multivariate data, with applications to financial data (2012) (Preprint) | MR | Zbl

[35] Kim, G.; Silvapulle, M.J.; Silvapulle, P. Comparison of semiparametric and parametric methods for estimating copulas, Computational Statistics and Data Analysis, Volume 51 (2007) no. 6, pp. 2836-2850 | MR | Zbl

[36] Kurowicka, D. Optimal Truncation of Vines, Dependence Modelling: Vine Copula Handbook, World Scientific Publishing Co. (2011) | MR

[37] Kojadinovic, I.; Yan, J. Modeling Multivariate Distributions with Continuous Margins Using the copula R Package, Journal of Statistical Software, Volume 34(9) (2010), pp. 1-20

[38] Kojadinovic, I.; Yan, J. A goodness-of-fit test for multivariate multiparameter copulas based on multiplier central limit theorems, Statistics and Computing, Volume 21 (2011), pp. 17-30 | MR | Zbl

[39] Kojadinovic, I.; Yan, J.; Holmes, M. Fast large-sample goodness-of-fit test for copulas, Statistica Sinica, Volume 21 (2011), pp. 841-871 | MR | Zbl

[40] Min, A.; Czado, C. Bayesian Inference for Multivariate Copulas Using Pair-Copula Constructions, Journal of Financial Econometrics, Volume 8 (2010) no. 4, pp. 511-546 | Zbl

[41] Morales-Nápoles, O.; Cooke, R.; Kurowicka, D. About the number of vines and regular vines on n nodes, Preprint (2010)

[42] Nelson, R.B. An Introduction to Copulas, Springer Science+Business Media, Inc., 2006 | MR | Zbl

[43] Nikoloulopoulos, A.K.; Joe, H.; Li, H. Vine copulas with asymmetric tail dependence and applications to financial return data, Computational Statistics & Data Analysis, Volume 56 (2012) no. 11, pp. 3659-3673 | MR | Zbl

[44] Panagiotelis, A.; Czado, C.; Joe, H. Pair Copula Constructions for Multivariate Discrete Data, Journal of the American Statistical Association, Volume 107 (2012) no. 499, pp. 1063-1072 | DOI | Zbl

[45] Schepsmeier, U.; Brechmann, E.C. CDVine: Statistical inference of C- and D-vine copulas (2012) (R package version 1.1-9)

[46] Stöber, J.; Czado, C. Detecting regime switches in the dependence stucture of high dimensional financial data (2013) (To appear in Computational Statistics & Data Analysis) | MR

[47] Stöber, J.; Joe, H.; Czado, C. Simplified pair copula constructions - limits and extensions (2012) (Preprint) | MR | Zbl

[48] Schepsmeier, U.; Stoeber, J.; Brechmann, E.C. VineCopula: Statistical inference of vine copulas (2012) (R package version 1.0)

[49] Vuong, Q.H. Ratio tests for model selection and non-nested hypotheses, Econometrica, Volume 57 (1989), pp. 307-333 | MR | Zbl