|
Activity Number:
|
521
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 10, 2006 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
WNAR
|
| Abstract - #304925 |
|
Title:
|
Analysis of Longitudinal Data with Semiparametric Estimation of Covariance Function
|
|
Author(s):
|
Runze Li*+ and Jianqing Fan and Tao Huang
|
|
Companies:
|
The Pennsylvania State University and Princeton University and Yale University
|
|
Address:
|
Department of Statistics, University Park, PA, 16802-2111,
|
|
Keywords:
|
kernel regression ; local linear regression ; profile weighted least squares ; semiparametric varying coefficient model
|
|
Abstract:
|
Two important aspects in analysis of longitudinal data are improving efficiency for regression coefficients and predicting trajectories of individuals. Both involve estimation of the covariance function. A class of semiparametric models for the covariance function is proposed by imposing parametric correlation structure while allowing nonparametric variance function. We introduce semiparametric-varying coefficient partially linear models for longitudinal data and propose an estimation procedure for their regression coefficients by using a profile-weighted least squares approach and an estimation procedure for variance function and parameters in correlation. We will study the sampling properties of the proposed procedures and assess their finite sample performance by Monte Carlo simulation. A real data example is used to illustrate the proposed methodology.
|
