Efficient Estimation of Longitudinal Data Additive Varying Coefficient Regression Models

• Published in: Acta Mathematicae Applicatae Sinica Vol. 33; no. 2; pp. 529 - 550
• Main Author: Liu, Shu
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2017; Springer Nature B.V
• Edition: English series
• Subjects: Applications of Mathematics; Asymptotic properties; Coefficients; Estimators; Math Applications in Computer Science; Mathematical and Computational Physics; Mathematics; Mathematics and Statistics; Regression models; Theoretical; additive vary-coefficient model; 62G08; within-subject correlation; 62G20; 62F12; 62H12; longitudinal data; modified Cholesky decomposition
• ISSN: 0168-9673; 1618-3932
• DOI: 10.1007/s10255-017-0681-2

We consider a longitudinal data additive varying coefficient regression model, in which the coef- ficients of some factors （covariates） are additive functions of other factors, so that the interactions between different factors can be taken into account effectively. By considering within-subject correlation among repeated measurements over time and additive structure, we propose a feasible weighted two-stage local quasi-likelihood estimation. In the first stage, we construct initial estimators of the additive component functions by B-spline se- ries approximation. With the initial estimators, we transform the additive varying coefficients regression model into a varying coefficients regression model and further apply the local weighted quasi-likelihood method to estimate the varying coefficient functions in the second stage. The resulting second stage estimators are com- putationally expedient and intuitively appealing. They also have the advantages of higher asymptotic efficiency than those neglecting the correlation structure, and an oracle property in the sense that the asymptotic property of each additive component is the same as if the other components were known with certainty. Simulation studies are conducted to demonstrate finite sample behaviors of the proposed estimators, and a real data example is given to illustrate the usefulness of the proposed methodology.