Acta mathematica scientia,Series A ›› 2010, Vol. 30 ›› Issue (1): 71-85.

• Articles • Previous Articles     Next Articles

Varying-Coefficient Partially Linear Models with Censored Data

LUO Xian-Hua, LI Yuan, MA Yun-Bei, ZHOU Yong   

  1. School of Mathematics and Information Science, Guangzhou University, Guangzhou 510006
  • Received:2007-11-30 Revised:2009-02-09 Online:2010-01-01 Published:2010-01-01
  • Supported by:

    罗和李的研究获得国家自然科学基金(10671044),广州市教育局项目(2004)和广州市科技局项目(2004J1-C0333)资助; 周和马的工作得到国家杰出青年基金项目(70825004), 国家杰出青年基金B项目(10721101)资助, 国家自然科学基金重点项目(10731010), 国家自然科学基金委创新研究群体科学基金(10721101),国家973项目子项目(2007CB814902)和国家自然科学基金委杰出青年基金B项目(10628104)资助. 并获得上海财经大学``十五''``211工程"重点学科建设项目和上海财经大学``211工程"期重点学科建设项目资助.

Abstract:

This paper considers varying-coefficient partially linear model, which allows one to examine the extent to which covariates interact
nonlinearly with an exposure variable, for analysis of censored data. It is very important and useful  to fit statistical models by linear construction for response and covariates. For censored data, the usual statistical techniques are not directly applicable to this model. In this paper, we propose a class of  transformations of the data so that a unbiased conditional expectation is established. Then the profile least-squares estimators for the parametric and nonparametric components are proposed by profile least-squares technique. The asymptotic normality of the proposed estimators are established. Some numerical examples are given to illustrate the effectiveness of the proposed procedures.

Key words: Varying-coefficient, Partially linear models,  Local linear regression, Profile least squares,  Censoring, Transformation

CLC Number: 

  • 62N05
Trendmd