Improving generalised estimating equations using quadratic inference functions

SUMMARY Generalised estimating equations enable one to estimate regression parameters consistently in longitudinal data analysis even when the correlation structure is misspecified. However, under such misspecification, the estimator of the regression parameter can be inefficient. In this paper we introduce a method of quadratic inference functions that does not involve direct estimation of the correlation parameter, and that remains optimal even if the working correlation structure is misspecified. The idea is to represent the inverse of the working correlation matrix by the linear combination of basis matrices, a representation that is valid for the working correlations most commonly used. Both asymptotic theory and simulation show that under misspecified working assumptions these estimators are more efficient than estimators from generalised estimating equations. This approach also provides a chi-squared inference function for testing nested models and a chi-squared regression misspecification test. Furthermore, the test statistic follows a chi-squared distribution asymptotically whether or not the working correlation structure is correctly specified.

[1]  Calyampudi R. Rao.  Large sample tests of statistical hypotheses concerning several parameters with applications to problems of estimation , 1948, Mathematical Proceedings of the Cambridge Philosophical Society.

[2]  Thomas S. Ferguson,et al.  A Method of Generating Best Asymptotically Normal Estimates with Application to the Estimation of Bacterial Densities , 1958 .

[3]  Justus Seely,et al.  Quadratic Subspaces and Completeness , 1971 .

[4]  P. McCullagh,et al.  Generalized Linear Models , 1972, Predictive Analytics.

[5]  T. W. Anderson.  Asymptotically Efficient Estimation of Covariance Matrices with Linear Structure , 1973 .

[6]  R. W. Wedderburn.  Quasi-likelihood functions, generalized linear models, and the Gauss-Newton method , 1974 .

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

[8]  B. Lindsay.  Conditional score functions: Some optimality results , 1982 .

[9]  P. McCullagh.  Quasi-Likelihood Functions , 1983 .

[10]  S. Zeger,et al.  Longitudinal data analysis using generalized linear models , 1986 .

[11]  N. Jewell,et al.  Hypothesis testing of regression parameters in semiparametric generalized linear models for cluster correlated data , 1990 .

[12]  P. McCullagh,et al.  Generalized Linear Models, 2nd Edn. , 1990 .

[13]  W. J. Hall,et al.  On large-sample estimation and testing in parametric models , 1990 .

[14]  L. Zhao,et al.  Estimating equations for parameters in means and covariances of multivariate discrete and continuous responses. , 1991, Biometrics.

[15]  John A. Nelder,et al.  Generalized linear models. 2nd ed. , 1993 .

[16]  C. Small,et al.  Hilbert Space Methods in Probability and Statistical Inference , 1994 .

[17]  Martin Crowder,et al.  On the use of a working correlation matrix in using generalised linear models for repeated measures , 1995 .

[18]  Myoung-jae Lee,et al.  Methods of moments and semiparametric econometrics for limited dependent variable models , 1996 .

[19]  Friedrich Götze,et al.  When is the Student $t$-statistic asymptotically standard normal? , 1997 .