Projected partial likelihood and its application to longitudinal data

SUMMARY An estimating equation, which we call the projected partial score, is introduced for longitudinal data analysis. The estimating equation is obtained by projecting the partial likelihood score function onto the vector space spanned by a class of 'conditionally linear' estimating equations. We demonstrate that removing certain terms from the projection of the full likelihood score does not alter important inferential properties of the estimating equation, and doing so is advantageous in handling missing data and time-varying covariates. Within a prequential frame of reference it is shown that the estimating equation is optimal among the largest collection of estimating equations determined by the conditional moments. Furthermore, the method possesses similar properties to generalised estimating equations; in particular, the correct conditional variance specification is necessary for efficiency but not for asymptotic consistency and distribution theory.

[1]  Ian W. McKeague,et al.  Weighted Least Squares Estimation for Aalen's Additive Risk Model , 1991 .

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

[3]  Thomas H. Scheike,et al.  Parametric regression for longitudinal data with counting process measurement times , 1994 .

[4]  G. Matanoski,et al.  The association between weight, physical activity, and stress and variation in the length of the menstrual cycle. , 1991, American journal of epidemiology.

[5]  W. Wong.  Theory of Partial Likelihood , 1986 .

[7]  P. Albert,et al.  Models for longitudinal data: a generalized estimating equation approach. , 1988, Biometrics.

[8]  A. Dawid.  Fisherian Inference in Likelihood and Prequential Frames of Reference , 1991 .

[9]  K Y Liang,et al.  Longitudinal data analysis for discrete and continuous outcomes. , 1986, Biometrics.

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

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

[12]  M. Kenward,et al.  Informative Drop‐Out in Longitudinal Data Analysis , 1994 .

[13]  C. Small,et al.  A projected likelihood function for semiparametric models , 1992 .

[14]  C. Small,et al.  The theory and applications of statistical inference functions , 1988 .

[15]  S A Murphy,et al.  An analysis for menstrual data with time-varying covariates. , 1995, Statistics in medicine.

[16]  Christopher G. Small,et al.  Hilbert Space Methods in Probability and Statistical Inference: Small/Hilbert , 1994 .

[17]  V. P. Godambe.  The foundations of finite sample estimation in stochastic processes , 1985 .

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

[19]  V. P. Godambe.  An Optimum Property of Regular Maximum Likelihood Estimation , 1960 .