Testing for time-invariant unobserved heterogeneity in generalized linear models for panel data

Recent literature on panel data emphasizes the importance of accounting for time-varying unobservable individual effects, which may stem from either omitted individual characteristics or macro-level shocks that affect each individual unit differently. In this paper, we propose a simple specification test of the null hypothesis that the individual effects are time-invariant against the alternative that they are time-varying. Our test is an application of Hausman (1978) testing procedure and can be used for any generalized linear model for panel data that admits a sufficient statistic for the individual effect. This is a wide class of models which includes the Gaussian linear model and a variety of nonlinear models typically employed for discrete or categorical outcomes. The basic idea of the test is to compare two alternative estimators of the model parameters based on two different formulations of the conditional maximum likelihood method. Our approach does not require assumptions on the distribution of unobserved heterogeneity, nor it requires the latter to be independent of the regressors in the model. We investigate the finite sample properties of the test through a set of Monte Carlo experiments. Our results show that the test performs well, with small size distortions and good power properties. We use a health economics example based on data from the Health and Retirement Study to illustrate the proposed test.

[1]  N. Reid,et al.  AN OVERVIEW OF COMPOSITE LIKELIHOOD METHODS , 2011 .

[2]  A. Cameron,et al.  Microeconometrics: Methods and Applications , 2005 .

[3]  C. Gourieroux,et al.  Pseudo Maximum Likelihood Methods: Applications to Poisson Models , 1984 .

[4]  Peter Schmidt,et al.  GMM estimation of linear panel data models with time-varying individual effects , 2001 .

[5]  Nicola Sartori,et al.  CONDITIONAL LIKELIHOOD INFERENCE IN GENERALIZED LINEAR MIXED MODELS , 2004 .

[6]  A. Farcomeni,et al.  A Multivariate Extension of the Dynamic Logit Model for Longitudinal Data Based on a Latent Markov Heterogeneity Structure , 2009 .

[7]  Lamar Pierce,et al.  Healthy, Wealthy, and Wise , 2014, Psychological science.

[8]  Seung C. Ahn,et al.  Panel Data Models with Multiple Time-Varying Individual Effects , 2013 .

[9]  M. Verbeek,et al.  Testing for selectivity bias in panel data models , 1992 .

[10]  D. Hyslop,et al.  State dependence, serial correlation and heterogeneity in intertemporal labor force , 1999 .

[11]  F. Bartolucci,et al.  Mixture latent autoregressive models for longitudinal data , 2011, 1108.1498.

[12]  Whitney K. Newey,et al.  Maximum Likelihood Specification Testing and Conditional Moment Tests , 1985 .

[13]  Alberto Holly,et al.  A Remark on Hausman's Specification Test , 1982 .

[14]  D. McFadden,et al.  "Healthy, Wealthy and Wise?" Revisited: An Analysis of the Causal Pathways from Socio-Economic Status to Health , 2011 .

[15]  Robin C. Sickles,et al.  A NEW PANEL DATA TREATMENT FOR HETEROGENEITY IN TIME TRENDS , 2012, Econometric Theory.

[16]  W. Newey,et al.  Estimating vector autoregressions with panel data , 1988 .

[17]  Florian Heiss.  Sequential numerical integration in nonlinear state space models for microeconometric panel data , 2008 .

[18]  Jeffrey M. Woodbridge.  Econometric Analysis of Cross Section and Panel Data , 2002 .

[19]  J. Pfanzagl.  On the consistency of conditional maximum likelihood estimators , 1993 .

[20]  P. Ruud.  Tests of specification in econometrics , 1984 .

[21]  Rainer Winkelmann,et al.  Consistent estimation of the fixed effects ordered logit model , 2015, SSRN Electronic Journal.

[22]  Z. Griliches,et al.  Econometric Models for Count Data with an Application to the Patents-R&D Relationship , 1984 .

[23]  Manuel Arellano,et al.  Nonlinear Panel Data Analysis , 2011 .

[24]  J. Hausman.  Specification tests in econometrics , 1978 .

[25]  M. Kendall.  Theoretical Statistics , 1956, Nature.

[26]  J. Bai,et al.  Panel Data Models With Interactive Fixed Effects , 2009 .

[27]  Cheng Hsiao,et al.  Analysis of Panel Data , 1987 .

[28]  C. Varin.  On composite marginal likelihoods , 2008 .

[29]  Brent R. Moulton.  Random group effects and the precision of regression estimates , 1986 .

[30]  H. White.  Maximum Likelihood Estimation of Misspecified Models , 1982 .

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

[32]  Gary Chamberlain,et al.  Efficiency Bounds for Semiparametric Regression , 1992 .

[33]  E. B. Andersen,et al.  Asymptotic Properties of Conditional Maximum‐Likelihood Estimators , 1970 .

[34]  Eric R. Ziegel,et al.  Generalized Linear Models , 2002, Technometrics.

[35]  Gary Chamberlain,et al.  Analysis of Covariance with Qualitative Data , 1979 .

[36]  Some useful equivalence properties of Hausman's test , 1986 .

[37]  C. Gouriéroux,et al.  PSEUDO MAXIMUM LIKELIHOOD METHODS: THEORY , 1984 .

[38]  N. Reid,et al.  On the robustness of maximum composite likelihood estimate , 2011 .

[39]  P. Diggle.  Analysis of Longitudinal Data , 1995 .