Modeling Dependence in High Dimensions With Factor Copulas

This article presents flexible new models for the dependence structure, or copula, of economic variables based on a latent factor structure. The proposed models are particularly attractive for relatively high-dimensional applications, involving 50 or more variables, and can be combined with semiparametric marginal distributions to obtain flexible multivariate distributions. Factor copulas generally lack a closed-form density, but we obtain analytical results for the implied tail dependence using extreme value theory, and we verify that simulation-based estimation using rank statistics is reliable even in high dimensions. We consider “scree” plots to aid the choice of the number of factors in the model. The model is applied to daily returns on all 100 constituents of the S&P 100 index, and we find significant evidence of tail dependence, heterogeneous dependence, and asymmetric dependence, with dependence being stronger in crashes than in booms. We also show that factor copula models provide superior estimates of some measures of systemic risk. Supplementary materials for this article are available online.

[1]  C. Czado,et al.  Modeling high dimensional time-varying dependence using D-vine SCAR models , 2012, 1202.2008.

[2]  Factor structures for panel and multivariate time series data , 2011 .

[3]  I. Olkin,et al.  Families of Multivariate Distributions , 1988 .

[4]  Daniel B. Nelson.  CONDITIONAL HETEROSKEDASTICITY IN ASSET RETURNS: A NEW APPROACH , 1991 .

[5]  Xiaohong Chen,et al.  Estimation and model selection of semiparametric copula-based multivariate dynamic models under copula misspecification , 2006 .

[6]  Dong Hwan Oh,et al.  Simulated Method of Moments Estimation for Copula-Based Multivariate Models , 2013 .

[7]  A. McNeil,et al.  The t Copula and Related Copulas , 2005 .

[8]  Andrew J. Patton.  Copula-Based Models for Financial Time Series , 2009 .

[9]  M. Rothschild,et al.  Arbitrage, Factor Structure, and Mean-Variance Analysis on Large Asset Markets , 1982 .

[10]  D. Andrews.  Testing When a Parameter Is on the Boundary of the Maintained Hypothesis , 2001 .

[11]  A. McNeil,et al.  The Grouped t-Copula with an Application to Credit Risk , 2003 .

[12]  GourierouxMonfort.  Statistics and Econometric Models, Volume 2 , 1996 .

[13]  T. Bollerslev,et al.  Generalized autoregressive conditional heteroskedasticity , 1986 .

[14]  B. McCarl,et al.  Economics , 1870, The Indian medical gazette.

[15]  Hugues Langlois,et al.  Dynamic Dependence and Diversification in Corporate Credit , 2016 .

[16]  Xiaohong Chen,et al.  Estimation of Copula-Based Semiparametric Time Series Models , 2006 .

[17]  Pavel Krupskii,et al.  Factor copula models for multivariate data , 2013, J. Multivar. Anal..

[18]  Alan G. White,et al.  Valuation of a CDO and an n-th to Default CDS Without Monte Carlo Simulation , 2004 .

[19]  J. Gregory,et al.  Basket Default Swaps, Cdos and Factor Copulas , 2005 .

[20]  M. Meerschaert.  Regular Variation in R k , 1988 .

[21]  Christian Gourieroux,et al.  Simulation-based econometric methods , 1996 .

[22]  Ruey S. Tsay,et al.  High Dimensional Dynamic Stochastic Copula Models , 2014 .

[23]  M. E. Johnson,et al.  A Family of Distributions for Modelling Non‐Elliptically Symmetric Multivariate Data , 1981 .

[24]  D. McFadden.  A Method of Simulated Moments for Estimation of Discrete Response Models Without Numerical Integration , 1989 .

[25]  D. Duffie,et al.  Frailty Correlated Default , 2006 .

[26]  Portfolio Selection with Heavy Tails , 2007 .

[27]  Ke Yu,et al.  Journal of the American Statistical Association Vast Volatility Matrix Estimation Using High- Frequency Data for Portfolio Selection Vast Volatility Matrix Estimation Using High-frequency Data for Portfolio Selection , 2022 .

[28]  B. Rémillard.  Goodness-ofFit Tests for Copulas of Multivariate Time Series , 2017 .

[29]  Dawn Hunter.  Basket default swaps, CDOs and factor copulas , 2005 .

[30]  A. Frigessi,et al.  Pair-copula constructions of multiple dependence , 2009 .

[31]  Paul Embrechts,et al.  Quantitative Risk Management , 2011, International Encyclopedia of Statistical Science.

[32]  B. Rémillard.  Goodness-of-Fit Tests for Copulas of Multivariate Time Series , 2010 .

[33]  R. Engle,et al.  Dynamic Equicorrelation , 2011 .

[34]  W. Newey,et al.  Large sample estimation and hypothesis testing , 1986 .

[35]  William Feller,et al.  An Introduction to Probability Theory and Its Applications , 1951 .

[36]  Nikolaus Hautsch,et al.  A Blocking and Regularization Approach to High Dimensional Realized Covariance Estimation , 2010 .

[37]  C. Klüppelberg,et al.  Modelling Extremal Events , 1997 .

[38]  Modelling Dynamic Portfolio Credit Risk , 2003 .

[39]  Satishs Iyengar,et al.  Multivariate Models and Dependence Concepts , 1998 .

[40]  J. Bai,et al.  Determining the Number of Factors in Approximate Factor Models , 2000 .

[41]  B. Hansen.  Autoregressive Conditional Density Estimation , 1994 .

[42]  Donald W. K. Andrews,et al.  Consistent Moment Selection Procedures for Generalized Method of Moments Estimation , 1999 .

[43]  Andrew J. Patton.  Modelling Asymmetric Exchange Rate Dependence , 2006 .

[44]  D. Pollard,et al.  Simulation and the Asymptotics of Optimization Estimators , 1989 .

[45]  Donald W. K. Andrews,et al.  Empirical Process Methods in Econometrics , 1993 .

[46]  R. Nelsen.  An Introduction to Copulas , 1998 .

[47]  Asymmetric CAPM dependence for large dimensions: the Canonical Vine Autoregressive Model , 2009 .

[48]  Christian Genest,et al.  Beyond simplified pair-copula constructions , 2012, J. Multivar. Anal..

[49]  Viral V. Acharya,et al.  Regulating Wall Street: The Dodd-Frank Act and the New Architecture of Global Finance , 2010 .

[50]  Leif B. G. Andersen,et al.  Extensions to the Gaussian Copula: Random Recovery and Random Factor Loadings , 2005 .

[51]  Claudia Klüppelberg,et al.  Copula structure analysis , 2009 .

[52]  Jón Dańıelsson,et al.  Fat tails, VaR and subadditivity☆ , 2013 .

[53]  Alexander J. McNeil,et al.  From Archimedean to Liouville copulas , 2010, J. Multivar. Anal..

[54]  R. Kohn,et al.  Modeling Dependence Using Skew T Copulas: Bayesian Inference and Applications , 2010 .

[55]  L. Hansen.  A method for calculating bounds on the asymptotic covariance matrices of generalized method of moments estimators , 1985 .

[56]  David X. Li.  On Default Correlation: A Copula Function Approach , 1999 .

[57]  Andrew J. Patton.  Copula Methods for Forecasting Multivariate Time Series , 2013 .

[58]  Andréas Heinen,et al.  Asymmetric CAPM Dependence for Large Dimensions: The Canonical Vine Autoregressive Copula Model , 2008 .

[59]  Alastair R. Hall,et al.  Generalized Method of Moments , 2005 .

[60]  Frank E. Grubbs,et al.  An Introduction to Probability Theory and Its Applications , 1951 .

[61]  T. Bollerslev,et al.  Modelling the Coherence in Short-run Nominal Exchange Rates: A Multivariate Generalized ARCH Model , 1990 .

[62]  W. Newey,et al.  Uniform Convergence in Probability and Stochastic Equicontinuity , 1991 .

[63]  R. Cattell.  The Scree Test For The Number Of Factors. , 1966, Multivariate behavioral research.

[64]  George S. Oldfield,et al.  The Economics of Structured Finance , 1997 .

[65]  F. Dias,et al.  Determining the number of factors in approximate factor models with global and group-specific factors , 2008 .

[66]  Christian Gourieroux,et al.  Statistics and econometric models , 1995 .

[67]  E. Luciano,et al.  Copula methods in finance , 2004 .

[68]  David M. Zimmer,et al.  The Role of Copulas in the Housing Crisis , 2012, Review of Economics and Statistics.

[69]  S. Kotz,et al.  The Meta-elliptical Distributions with Given Marginals , 2002 .

[70]  Hugues Langlois,et al.  Is the Potential for International Diversi?cation Disappearing? A Dynamic Copula Approach , 2012 .

[71]  David X. Li.  On Default Correlation , 2000 .

[72]  O. Barndorff-Nielsen.  Normal Inverse Gaussian Distributions and Stochastic Volatility Modelling , 1997 .

[73]  Zhi-Xian Gao,et al.  Flow Injection Determination of Nitrite in Food Samples by Dialysis Membrane Separation and Photometric Detection , 2002 .

[74]  E. Luciano,et al.  Copula Methods in Finance: Cherubini/Copula , 2004 .

[75]  H. White,et al.  A Reality Check for Data Snooping , 2000 .

[76]  B. Harshbarger.  An Introduction to Probability Theory and its Applications, Volume I , 1958 .

[77]  K. Judd.  Numerical methods in economics , 1998 .

[78]  Peter F. Christoffersen,et al.  Is the Potential for International Diversification Disappearing? , 2010 .

[79]  C. Czado,et al.  Bayesian inference for multivariate copulas using pair-copula constructions. , 2010 .

[80]  Jianqing Fan,et al.  High dimensional covariance matrix estimation using a factor model , 2007, math/0701124.

[81]  Peter F. Christoffersen,et al.  Dynamic Dependence in Corporate Credit , 2013 .

[82]  Halbert White,et al.  Estimation, inference, and specification analysis , 1996 .

[83]  Robert F. Engle,et al.  Fitting Vast Dimensional Time-Varying Covariance Models , 2017, Journal of Business & Economic Statistics.

[84]  Robert F. Engle,et al.  Volatility, Correlation and Tails for Systemic Risk Measurement , 2012 .

[85]  M. Wegkamp,et al.  Weak Convergence of Empirical Copula Processes , 2004 .

[86]  Stefan Straetmans,et al.  Banking System Stability: A Cross-Atlantic Perspective , 2005, SSRN Electronic Journal.

[87]  L. Glosten,et al.  On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks , 1993 .