Dynamic Factor Copula Models with Estimated Cluster Assignments

This paper proposes a dynamic multi-factor copula for use in high dimensional time series applications. A novel feature of our model is that the assignment of individual variables to groups is estimated from the data, rather than being pre-assigned using SIC industry codes, market capitalization ranks, or other ad hoc methods. We adapt the k-means clustering algorithm for use in our application and show that it has excellent finite-sample properties. Applying the new model to returns on 110 US equities, we find around 20 clusters to be optimal. In out-of-sample forecasts, we find that a model with as few as five estimated clusters significantly outperforms an otherwise identical model with 21 clusters formed using two-digit SIC codes.

[1]  R. Engle.  Dynamic Conditional Correlation : A Simple Class of Multivariate GARCH Models , 2000 .

[2]  Andrew J. Patton,et al.  Risk Price Variation: The Missing Half of Empirical Asset Pricing , 2019 .

[3]  Halbert White,et al.  Tests of Conditional Predictive Ability , 2003 .

[4]  Modelling Dependence in High Dimensions with Factor Copulas , 2015 .

[5]  Andrew J. Patton,et al.  Time-Varying Systemic Risk: Evidence From a Dynamic Copula Model of CDS Spreads , 2013 .

[6]  Elena Manresa,et al.  Grouped Patterns of Heterogeneity in Panel Data , 2015 .

[7]  Liangjun Su,et al.  Sieve Estimation of Time-Varying Panel Data Models With Latent Structures , 2019 .

[8]  W. Newey,et al.  A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelationconsistent Covariance Matrix , 1986 .

[9]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

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

[11]  Xiaohong Chen,et al.  MIXING AND MOMENT PROPERTIES OF VARIOUS GARCH AND STOCHASTIC VOLATILITY MODELS , 2002, Econometric Theory.

[12]  Andrew Ang,et al.  Asymmetric Correlations of Equity Portfolios , 2001 .

[13]  Christian M. Hafner,et al.  On asymptotic theory for multivariate GARCH models , 2009, J. Multivar. Anal..

[14]  O. Linton,et al.  Multiscale clustering of nonparametric regression curves , 2018, Journal of Econometrics.

[15]  Guofu Zhou,et al.  Asymmetries in Stock Returns: Statistical Tests and Economic Evaluation , 2003 .

[16]  Michael T. Owyang,et al.  An Endogenously Clustered Factor Approach to International Business Cycles , 2012 .

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

[18]  Qiwei Yao,et al.  Large Volatility Matrix Inference via Combining Low-Frequency and High-Frequency Approaches , 2011 .

[19]  P. Phillips,et al.  Identifying Latent Structures in Panel Data , 2014 .

[20]  A. Opschoor,et al.  Closed-Form Multi-Factor Copula Models With Observation-Driven Dynamic Factor Loadings , 2019, Journal of Business & Economic Statistics.

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

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

[23]  Andrew J. Patton.  On the Out-of-Sample Importance of Skewness and Asymmetric Dependence for Asset Allocation , 2002 .

[24]  Klaus Nordhausen,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition by Trevor Hastie, Robert Tibshirani, Jerome Friedman , 2009 .

[25]  Serena Ng,et al.  Estimation of Panel Data Models with Parameter Heterogeneity when Group Membership is Unknown , 2007 .

[26]  Drew D. Creal,et al.  Generalized autoregressive score models with applications ∗ , 2010 .

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

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

[29]  Andrew Harvey,et al.  Dynamic Models for Volatility and Heavy Tails , 2013 .

[30]  A. Raftery,et al.  Strictly Proper Scoring Rules, Prediction, and Estimation , 2007 .

[31]  Raffaello Seri,et al.  Estimation in Discrete Parameter Models , 2012, 1207.5653.

[32]  Casado del Alisal.  Is a normal copula the right copula ? , 2015 .

[33]  Christian Hansen,et al.  Grouped effects estimators in fixed effects models , 2016 .

[34]  Kay Giesecke,et al.  Systemic Risk: What Defaults are Telling Us , 2009, Manag. Sci..

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

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

[37]  Jianqing Fan,et al.  Large covariance estimation by thresholding principal orthogonal complements , 2011, Journal of the Royal Statistical Society. Series B, Statistical methodology.

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