1932

Abstract

With the availability of massive multivariate data comes a need to develop flexible multivariate distribution classes. The copula approach allows marginal models to be constructed for each variable separately and joined with a dependence structure characterized by a copula. The class of multivariate copulas was limited for a long time to elliptical (including the Gaussian and -copula) and Archimedean families (such as Clayton and Gumbel copulas). Both classes are rather restrictive with regard to symmetry and tail dependence properties. The class of vine copulas overcomes these limitations by building a multivariate model using only bivariate building blocks. This gives rise to highly flexible models that still allow for computationally tractable estimation and model selection procedures. These features made vine copula models quite popular among applied researchers in numerous areas of science. This article reviews the basic ideas underlying these models, presents estimation and model selection approaches, and discusses current developments and future directions.

Loading

Article metrics loading...

/content/journals/10.1146/annurev-statistics-040220-101153
2022-03-07
2024-05-27
Loading full text...

Full text loading...

/deliver/fulltext/statistics/9/1/annurev-statistics-040220-101153.html?itemId=/content/journals/10.1146/annurev-statistics-040220-101153&mimeType=html&fmt=ahah

Literature Cited

  1. Aas K. 2016. Pair-copula constructions for financial applications: a review. Econometrics 4:443
    [Google Scholar]
  2. Aas K, Czado C, Frigessi A, Bakken H 2009. Pair-copula constructions of multiple dependence. Insur. Math. Econ. 44:2182–98
    [Google Scholar]
  3. Aas K, Nagler T, Jullum M, Løland A. 2021. Explaining predictive models using Shapley values and non-parametric vine copulas. arXiv:2102.06416 [stat.ME]
  4. Acar EF, Craiu RV, Yao F et al. 2013. Statistical testing of covariate effects in conditional copula models. Electron. J. Stat. 7:2822–50
    [Google Scholar]
  5. Acar EF, Czado C, Lysy M. 2019. Flexible dynamic vine copula models for multivariate time series data. Econom. Stat. 12:181–97
    [Google Scholar]
  6. Acar EF, Genest C, Nešlehová J. 2012. Beyond simplified pair-copula constructions. J. Multivar. Anal. 110:74–90
    [Google Scholar]
  7. Almeida C, Czado C, Manner H. 2016. Modeling high-dimensional time-varying dependence using dynamic D-vine models. Appl. Stoch. Models Bus. Ind. 32:5621–38
    [Google Scholar]
  8. Barthel N, Geerdens C, Czado C, Janssen P. 2017. Modeling recurrent event times subject to right-censoring with D-vine copulas. arXiv:1712.05845 [stat.ME]
  9. Barthel N, Geerdens C, Killiches M, Janssen P, Czado C. 2018. Vine copula based likelihood estimation of dependence patterns in multivariate event time data. Comput. Stat. Data Anal. 117:109–27
    [Google Scholar]
  10. Beare BK, Seo J. 2015. Vine copula specifications for stationary multivariate Markov chains. J. Time Ser. Anal. 36:2228–46
    [Google Scholar]
  11. Bedford T, Cooke RM. 2001. Probability density decomposition for conditionally dependent random variables modeled by vines. Ann. Math. Artif. Intell. 32:245–68
    [Google Scholar]
  12. Bedford T, Cooke RM. 2002. Vines: a new graphical model for dependent random variables. Ann. Stat. 30:41031–68
    [Google Scholar]
  13. Bernard C, Czado C. 2015. Conditional quantiles and tail dependence. J. Multivar. Anal. 138:104–26
    [Google Scholar]
  14. Bevacqua E. 2017. CDVineCopulaConditional: sampling from conditional C- and D-vine copulas. R Package version 0.1.0. https://CRAN.R-project.org/package=CDVineCopulaConditional
    [Google Scholar]
  15. Brechmann EC, Czado C. 2013. Risk management with high-dimensional vine copulas: an analysis of the Euro Stoxx 50. Stat. Risk Model. 30:4307–42
    [Google Scholar]
  16. Brechmann EC, Czado C. 2015. COPAR—multivariate time series modeling using the copula autoregressive model. Appl. Stoch. Models Bus. Ind. 31:4495–514
    [Google Scholar]
  17. Brechmann EC, Czado C, Aas K. 2012. Truncated regular vines and their applications. Can. J. Stat. 40:168–85
    [Google Scholar]
  18. Brechmann EC, Joe H. 2015. Truncation of vine copulas using fit indices. J. Multivar. Anal. 138:19–33
    [Google Scholar]
  19. Carrera D, Bandeira L, Santana R, Lozano JA 2019. Detection of sand dunes on mars using a regular vine-based classification approach. Knowl. Based Syst. 163:858–74
    [Google Scholar]
  20. Carrera D, Santana R, Lozano JA 2016. Vine copula classifiers for the mind reading problem. Prog. Artif. Intell. 5:4289–305
    [Google Scholar]
  21. Chang B, Joe H 2019. Prediction based on conditional distributions of vine copulas. Comput. Stat. Data Anal. 139:45–63
    [Google Scholar]
  22. Chang B, Pan S, Joe H 2019. Vine copula structure learning via Monte Carlo tree search. Proc. Mach. Learn. Res. 89:353–61
    [Google Scholar]
  23. Chen Y. 2016. A copula-based supervised learning classification for continuous and discrete data. J. Data Sci. 14:4769–82
    [Google Scholar]
  24. Chollete L, Heinen A, Valdesogo A. 2009. Modeling international financial returns with a multivariate regime-switching copula. J. Financ. Econom. 7:4437–80
    [Google Scholar]
  25. Coblenz M. 2021. MATVines: a vine copula package for MATLAB. SoftwareX 14:100700
    [Google Scholar]
  26. Cooke RM, Joe H, Chang B 2019. Vine copula regression for observational studies. AStA Adv. Stat. Anal. 104:141–67
    [Google Scholar]
  27. Cooke RM, Kurowicka D, Wilson K 2015. Sampling, conditionalizing, counting, merging, searching regular vines. J. Multivar. Anal. 138:4–18
    [Google Scholar]
  28. Cuvelier E, Noirhomme-Fraiture M 2005. Clayton copula and mixture decomposition. Applied Stochastic Models and Data Analysis (ASMDA 2005) J Janssen, P Lenca 699–708 Bretagne, Fr: ENST
    [Google Scholar]
  29. Czado C. 2019. Analyzing Dependent Data with Vine Copulas: A Practical Guide with R New York: Springer
  30. Czado C, Brechmann EC, Gruber L 2013. Selection of vine copulas. Copulae in Mathematical and Quantitative Finance P Jaworski, F Durante, WK Härdle 17–37 New York: Springer
    [Google Scholar]
  31. Czado C, Schepsmeier U, Min A. 2012. Maximum likelihood estimation of mixed C-vines with application to exchange rates. Stat. Model. 12:3229–55
    [Google Scholar]
  32. De Backer M, El Ghouch A, Van Keilegom I 2017. Semiparametric copula quantile regression for complete or censored data. Electron. J. Stat. 11:11660–98
    [Google Scholar]
  33. Dempster AP, Laird NM, Rubin DB 1977. Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B 39:11–22
    [Google Scholar]
  34. Derumigny A, Fermanian JD. 2017. About tests of the ``simplifying'' assumption for conditional copulas. Depend. Model. 5:1154–97
    [Google Scholar]
  35. Diday E 2002. Mixture decomposition of distributions by copulas. Classification, Clustering, and Data Analysis: Recent Advances and Applications K Jajuga, A Sokołowski, H-H Bock 297–310 New York: Springer
    [Google Scholar]
  36. Dissmann J, Brechmann EC, Czado C, Kurowicka D 2013. Selecting and estimating regular vine copulae and application to financial returns. Comput. Stat. Data Anal. 59:52–69
    [Google Scholar]
  37. Elidan G. 2012. Copula network classifiers (CNCs). Proc. Mach. Learn. Res. 22:346–54
    [Google Scholar]
  38. Engle R. 2002. Dynamic conditional correlation: a simple class of multivariate generalized autoregressive conditional heteroskedasticity models. J. Bus. Econ. Stat. 20:3339–50
    [Google Scholar]
  39. Fink H, Klimova Y, Czado C, Stöber J 2017. Regime switching vine copula models for global equity and volatility indices. Econometrics 5:13
    [Google Scholar]
  40. Fraley C, Raftery AE. 2002. Model-based clustering, discriminant analysis, and density estimation. J. Am. Stat. Assoc. 97:458611–31
    [Google Scholar]
  41. Genest C, Favre AC. 2007. Everything you always wanted to know about copula modeling but were afraid to ask. J. Hydrol. Eng. 12:4347–68
    [Google Scholar]
  42. Genest C, Ghoudi K, Rivest L 1995. A semi-parametric estimation procedure of dependence parameters in multivariate families of distributions. Biometrika 82:543–52
    [Google Scholar]
  43. Genest C, Nešlehová J, Ben Ghorbal N. 2011. Estimators based on Kendall's tau in multivariate copula models. Aust. N. Z. J. Stat. 53:2157–77
    [Google Scholar]
  44. Gijbels I, Omelka M, Veraverbeke N. 2017. Nonparametric testing for no covariate effects in conditional copulas. Statistics 51:3475–509
    [Google Scholar]
  45. Goel A, Mehra A. 2019. Analyzing contagion effect in markets during financial crisis using stochastic autoregressive canonical vine model. Comput. Econ. 53:3921–50
    [Google Scholar]
  46. Gruber L, Czado C. 2015. Sequential Bayesian model selection of regular vine copulas. Bayesian Anal. 10:4937–63
    [Google Scholar]
  47. Gruber L, Czado C. 2018. Bayesian model selection of regular vine copulas. Bayesian Anal. 13:41111–35
    [Google Scholar]
  48. Haff IH. 2013. Parameter estimation for pair-copula constructions. Bernoulli 19:2462–91
    [Google Scholar]
  49. Haff IH, Segers J. 2015. Nonparametric estimation of pair-copula constructions with the empirical pair-copula. Comput. Stat. Data Anal. 84:1–13
    [Google Scholar]
  50. Han D, Tan KS, Weng C. 2017. Vine copula models with GLM and sparsity. Commun. Stat. Theory Methods 46:136358–81
    [Google Scholar]
  51. Hobæk Haff I, Aas K, Frigessi A 2010. On the simplified pair-copula construction—simply useful or too simplistic?. J. Multivar. Anal. 101:51296–310
    [Google Scholar]
  52. Jäger WS, Nagler T, Czado C, McCall RT 2019. A statistical simulation method for joint time series of non-stationary hourly wave parameters. Coastal Eng. 146:14–31
    [Google Scholar]
  53. Joe H 1996. 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, B Schweizer, MD Taylor 120–41 N.p.: Inst. Math. Stat.
    [Google Scholar]
  54. Joe H. 1997. Multivariate Models and Dependence Concepts London: Chapman and Hall
  55. Joe H. 2005. Asymptotic efficiency of the two stage estimation method for copula-based models. J. Multivar. Anal. 94:401–19
    [Google Scholar]
  56. Joe H. 2014. Dependence Modeling with Copulas Boca Raton, FL: Chapman and Hall/CRC
  57. Joe H. 2018. Parsimonious graphical dependence models constructed from vines. Can. J. Stat. 46:4532–55
    [Google Scholar]
  58. Killiches M, Kraus D, Czado C. 2017. Examination and visualisation of the simplifying assumption for vine copulas in three dimensions. Aust. N. Z. J. Stat. 59:195–117
    [Google Scholar]
  59. Kim D, Kim JM, Liao SM, Jung YS. 2013. Mixture of D-vine copulas for modeling dependence. Comput. Stat. Data Anal. 64:1–19
    [Google Scholar]
  60. Kirshner S 2008. Learning with tree-averaged densities and distributions. NIPS'07: Proceedings of the 20th International Conference on Neural Information Processing Systems JC Platt, D Koller, Y Singer, ST Roweis 761–68 Red Hook, NY: Curran
  61. Koenker R, Bassett G. 1978. Regression quantiles. J. Econom. Soc. 46:33–50
    [Google Scholar]
  62. Kraus D, Czado C. 2017a. D-vine copula based quantile regression. Comput. Stat. Data Anal. 110:1–18
    [Google Scholar]
  63. Kraus D, Czado C. 2017b. Growing simplified vine copula trees: improving Dißmann's algorithm. arXiv:1703.05203 [stat.ME]
  64. Kreuzer A, Czado C. 2019. Bayesian inference for dynamic vine copulas in higher dimensions. arXiv:1911.00702 [stat.ME]
  65. Kreuzer A, Czado C. 2021. Bayesian inference for a single factor copula stochastic volatility model using Hamiltonian Monte Carlo. Econom. Stat. 19:130–50
    [Google Scholar]
  66. Kurowicka D 2011. Optimal truncation of vines. Dependence Modeling: Vine Copula Handbook D Kurowicka, H Joe 233–47 Singapore: World Sci.
    [Google Scholar]
  67. Kurowicka D, Cooke R. 2006. Uncertainty Analysis with High Dimensional Dependence Modelling New York: Wiley
  68. Kurz M. 2015. VineCopulaMATLAB: a MATLAB toolbox for vine copulas based on C++. MATLAB Toolbox https://maltekurz.github.io/VineCopulaMatlab/
    [Google Scholar]
  69. Kurz MS. 2017. pacotest: Testing for partial copulas and the simplifying assumption in vine copulas. R package version 0.2.2. https://CRAN.R-project.org/package=pacotest
    [Google Scholar]
  70. Kurz MS, Spanhel F. 2018. Testing the simplifying assumption in high-dimensional vine copulas. arXiv:1706.02338 [stat.ME]
  71. Meng XL, Rubin DB. 1993. Maximum likelihood estimation via the ECM algorithm: a general framework. Biometrika 80:2267–78
    [Google Scholar]
  72. Min A, Czado C 2014. SCOMDY models based on pair-copula constructions with application to exchange rates. Comput. Stat. Data Anal. 76:523–35
    [Google Scholar]
  73. Morales-Nápoles O 2011. Counting vines. Dependence Modeling: Vine Copula Handbook D Kurowicka, H Joe 189–218 Singapore: World Sci.
    [Google Scholar]
  74. Mroz T, Fuchs S, Trutschnig W. 2021. How simplifying and flexible is the simplifying assumption in pair-copula constructions—analytic answers in dimension three and a glimpse beyond. Electron. J. Stat. 15:11951–92
    [Google Scholar]
  75. Müller D, Czado C. 2018. Representing sparse Gaussian DAGs as sparse R-vines allowing for non-Gaussian dependence. J. Comput. Graph. Stat. 27:2334–44
    [Google Scholar]
  76. Müller D, Czado C. 2019a. Dependence modelling in ultra high dimensions with vine copulas and the graphical lasso. Comput. Stat. Data Anal. 137:211–32
    [Google Scholar]
  77. Müller D, Czado C. 2019b. Selection of sparse vine copulas in high dimensions with the lasso. Stat. Comput. 29:2269–87
    [Google Scholar]
  78. Nagler T. 2018. kdecopula: an R package for the kernel estimation of bivariate copula densities. J. Stat. Softw. 84:71–22
    [Google Scholar]
  79. Nagler T, Bumann C, Czado C. 2019. Model selection in sparse high-dimensional vine copula models with an application to portfolio risk. J. Multivar. Anal. 172:180–92
    [Google Scholar]
  80. Nagler T, Czado C. 2016. Evading the curse of dimensionality in nonparametric density estimation with simplified vine copulas. J. Multivar. Anal. 151:69–89
    [Google Scholar]
  81. Nagler T, Krüger D, Min A 2020a. Stationary vine copula models for multivariate time series. arXiv:2008.05990 [stat.ME]
  82. Nagler T, Schellhase C, Czado C. 2017. Nonparametric estimation of simplified vine copula models: comparison of methods. Depend. Model. 5:99–120
    [Google Scholar]
  83. Nagler T, Schepsmeier U, Stöber J, Brechmann EC, Graeler B, Erhardt T 2020b. VineCopula: statistical inference of vine copulas. R package version 2.4.1. https://CRAN.R-project.org/package=VineCopula
    [Google Scholar]
  84. Nagler T, Vatter T. 2020a. rvinecopulib: high performance algorithms for vine copula modeling. R package version 0.5.5.1.1. https://CRAN.R-project.org/package=rvinecopulib
    [Google Scholar]
  85. Nagler T, Vatter T. 2020b. Solving estimating equations with copulas. arXiv:1801.10576 [stat.ME]
  86. Nagler T, Vatter T. 2020c. vinecopulib: high performance algorithms for vine copula modeling. C++ library version 0.5.5
    [Google Scholar]
  87. Nelsen RB. 2007. An Introduction to Copulas New York: Springer
  88. Noh H, El Ghouch A, Van Keilegom I. 2015. Semiparametric conditional quantile estimation through copula-based multivariate models. J. Bus. Econ. Stat. 33:2167–78
    [Google Scholar]
  89. Panagiotelis A, Czado C, Joe H. 2012. Pair copula constructions for multivariate discrete data. J. Am. Stat. Assoc. 107:4991063–72
    [Google Scholar]
  90. Portier F, Segers J. 2018. On the weak convergence of the empirical conditional copula under a simplifying assumption. J. Multivar. Anal. 166:160–81
    [Google Scholar]
  91. Rosenblatt M. 1952. Remarks on a multivariate transformation. Ann. Math. Stat. 23:3470–72
    [Google Scholar]
  92. Roy A, Parui SK 2014. Pair-copula based mixture models and their application in clustering. Pattern Recognit. 47:41689–97
    [Google Scholar]
  93. Sahin Ö, Czado C. 2021. Vine copula mixture models and clustering for non-Gaussian data. arXiv:2102.03257 [stat.ME]
  94. Salinas-Gutiérrez R, Hernández-Quintero A, Dalmau-Cedeño O, Pérez-Daz ÁP 2017. Modeling dependencies in supervised classification. Mexican Conference on Pattern Recognition JA Carrasco-Ochoa, JF Martínez-Trinidad, JA Olvera-López 117–26 New York: Springer
  95. Schallhorn N, Kraus D, Nagler T, Czado C. 2017. D-vine quantile regression with discrete variables. arXiv:1705.08310 [stat.ME]
  96. Schellhase C. 2017. pencopulaCond: estimating non-simplified vine copulas using penalized splines. R package version 0.2
    [Google Scholar]
  97. Schellhase C, Spanhel F. 2018. Estimating non-simplified vine copulas using penalized splines. Stat. Comput. 28:2387–409
    [Google Scholar]
  98. Schepsmeier U, Stöber J. 2014. Derivatives and Fisher information of bivariate copulas. Stat. Pap. 55:2525–42
    [Google Scholar]
  99. Silva R, Gramacy R. 2009. MCMC methods for Bayesian mixtures of copulas. Proc. Mach. Learn. Res. 5:512–19
    [Google Scholar]
  100. Sklar A. 1959. Fonctions de répartition à n dimensions et leurs marges. Publ. Inst. Stat. Univ. Paris 8:229–31
    [Google Scholar]
  101. Smith MS. 2015. Copula modelling of dependence in multivariate time series. Int. J. Forecast. 31:3815–33
    [Google Scholar]
  102. So MK, Yeung CY. 2014. Vine-copula GARCH model with dynamic conditional dependence. Comput. Stat. Data Anal. 76:655–71
    [Google Scholar]
  103. Spanhel F, Kurz MS et al. 2019. Simplified vine copula models: approximations based on the simplifying assumption. Electron. J. Stat. 13:11254–91
    [Google Scholar]
  104. Stöber J. 2013. Regular vine copulas with the simplifying assumption, time-variation, and mixed discrete and continuous margins. Ph.D. Thesis Dep. Math., Tech. Univ. Munich Munich, Ger:.
    [Google Scholar]
  105. Stöber J, Czado C. 2014. Regime switches in the dependence structure of multidimensional financial data. Comput. Stat. Data Anal. 76:672–86
    [Google Scholar]
  106. Stöber J, Hong HG, Czado C, Ghosh P. 2015. Comorbidity of chronic diseases in the elderly: patterns identified by a copula design for mixed responses. Comput. Stat. Data Anal. 88:28–39
    [Google Scholar]
  107. Stöber J, Joe H, Czado C. 2013. Simplified pair copula constructions—limitations and extensions. J. Multivar. Anal. 119:101–18
    [Google Scholar]
  108. Stöber J, Schepsmeier U. 2013. Estimating standard errors in regular vine copula models. Comput. Stat. 28:62679–707
    [Google Scholar]
  109. Sun M, Konstantelos I, Strbac G 2017. C-vine copula mixture model for clustering of residential electrical load pattern data. IEEE Trans. Power Syst. 32:32382–93
    [Google Scholar]
  110. Sun Y, Cuesta-Infante A, Veeramachaneni K. 2019. Learning vine copula models for synthetic data generation. Thirty-Fifth AAAI Conference on Artificial Intelligence5049–57 Palo Alto, CA: AAAI
  111. Tagasovska N, Ackerer D, Vatter T 2019. Copulas as high-dimensional generative models: vine copula autoencoders. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) H Wallach, H Larochelle, A Beygelzimer, F d'Alché-Buc, E Fox, R Garnett Red Hook, NY: Curran
  112. Tekumalla LS, Rajan V, Bhattacharyya C 2017. Vine copulas for mixed data: multi-view clustering for mixed data beyond meta-Gaussian dependencies. Mach. Learn. 106:91331–57
    [Google Scholar]
  113. Tepegjozova M, Zhou J, Claeskens G, Czado C. 2021. Nonparametric C-and D-vine based quantile regression. arXiv:2102.04873 [stat.ME]
  114. Vatter T, Nagler T. 2017. gamCopula: generalized additive models for bivariate conditional dependence structures and vine copulas. R package version 0.0-4. https://CRAN.R-project.org/package=gamCopula
    [Google Scholar]
  115. Vatter T, Nagler T. 2018. Generalized additive models for pair-copula constructions. J. Comput. Graph. Stat. 27:4715–27
    [Google Scholar]
  116. Vatter T, Nagler T, Arabas S. 2020. pyvinecopulib. Python library version 0.5.5. https://pypi.org/project/pyvinecopulib
    [Google Scholar]
  117. Vrac M, Chédin A, Diday E 2005. Clustering a global field of atmospheric profiles by mixture decomposition of copulas. J. Atmos. Ocean. Technol. 22:101445–59
    [Google Scholar]
  118. Yuan Z, Hu T. 2019. pyvine: the Python package for regular vine copula modeling, sampling and testing. Commun. Math. Stat. 9:53–86
    [Google Scholar]
  119. Zhu K, Kurowicka D, Nane GF. 2020. Common sampling orders of regular vines with application to model selection. Comput. Stat. Data Anal. 142:106811
    [Google Scholar]
  120. Zhu K, Kurowicka D, Nane GF. 2021. Simplified R-vine based forward regression. Comput. Stat. Data Anal. 155:107091
    [Google Scholar]
/content/journals/10.1146/annurev-statistics-040220-101153
Loading
/content/journals/10.1146/annurev-statistics-040220-101153
Loading

Data & Media loading...

  • Article Type: Review Article
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error