Testing for Common Conditionally Heteroskedastic Factors

This paper proposes a test for common conditionally heteroskedastic (CH) features in asset returns. Following Engle and Kozicki (1993), the common CH features property is expressed in terms of testable overidentifying moment restrictions. However, as we show, these moment conditions have a degenerate Jacobian matrix at the true parameter value and therefore the standard asymptotic results of Hansen (1982) do not apply. We show in this context that Hansen's (1982) J-test statistic is asymptotically distributed as the minimum of the limit of a certain random process with a markedly nonstandard distribution. If two assets are considered, this asymptotic distribution is a fifty-fifty mixture of ... and ..., where H is the number of moment conditions, as opposed to a .... With more than two assets, this distribution lies between the ... and ... (p denotes the number of parameters). These results show that ignoring the lack of first-order identification of the moment condition model leads to oversized tests with a possibly increasing overrejection rate with the number of assets. A Monte Carlo study illustrates these findings. (ProQuest: ... denotes formulae/symbols omitted.)

[1]  É. Renault,et al.  Factor Stochastic Volatility in Mean Models: A GMM Approach , 2006 .

[2]  Lung-fei Lee,et al.  Specification testing when score test statistics are identically zero , 1986 .

[3]  Stephen G. Donald,et al.  Testing Identifiability and Specification in Instrumental Variable Models , 1993, Econometric Theory.

[4]  Alexander Lindner,et al.  Stationarity, Mixing, Distributional Properties and Moments of GARCH(p, q)-Processes , 2009 .

[5]  D. Andrews,et al.  Estimation and Inference with Weak, Semi-Strong, and Strong Identification , 2010 .

[6]  L. Hansen.  Large Sample Properties of Generalized Method of Moments Estimators , 1982 .

[7]  É. Renault,et al.  GMM Overidentification Test with First Order Underidentification , 2009 .

[8]  G. Chamberlain.  Asymptotic efficiency in semi-parametric models with censoring , 1986 .

[9]  Zhongjun Qu.  Inference and Speci?cation Testing in DSGE Models with Possible Weak Identification , 2011 .

[10]  J. Stock,et al.  Instrumental Variables Regression with Weak Instruments , 1994 .

[11]  J. D. Sargan,et al.  Identification and lack of identification , 1983 .

[12]  Gabriele Fiorentini,et al.  Likelihood-based estimation of latent generalised ARCH structures , 2004 .

[13]  J. Robins,et al.  Likelihood-based inference with singular information matrix , 2000 .

[14]  F. Diebold,et al.  The dynamics of exchange rate volatility: a multivariate latent factor ARCH model , 1986 .

[15]  Jonathan H. Wright,et al.  GMM WITH WEAK IDENTIFICATION , 2000 .

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

[17]  S. Laurent,et al.  On the Univariate Representation of BEKK Models with Common Factors , 2015 .

[18]  M. Rothschild,et al.  Asset Pricing with a Factor Arch Covariance Structure: Empirical Estimates for Treasury Bills , 1988 .

[19]  Anna Mikusheva,et al.  Maximum Likelihood Inference in Weakly Identified DSGE Models , 2011 .

[20]  P. Billingsley,et al.  The Lindeberg-Lévy theorem for martingales , 1961 .

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

[22]  Robert F. Engle,et al.  Common Volatility in International Equity Markets , 1993 .

[23]  H. Koul.  Weighted Empirical Processes in Dynamic Nonlinear Models , 2002 .

[24]  Angelo Melino,et al.  Testing for Sample Selection Bias , 1982 .

[25]  Bent E. Sørensen,et al.  GMM Estimation of a Stochastic Volatility Model: A Monte Carlo Study , 1996 .