Affordable Access

Publisher Website

Estimation of the marginal location under a partially linear model with missing responses

Authors
Journal
Computational Statistics & Data Analysis
0167-9473
Publisher
Elsevier
Publication Date
Volume
54
Issue
2
Identifiers
DOI: 10.1016/j.csda.2009.09.028

Abstract

Abstract In this paper, we consider a semiparametric partially linear regression model where there are missing data in the response. We propose robust Fisher-consistent estimators for the regression parameter, for the regression function and for the marginal location parameter of the response variable. A robust cross-validation method is briefly discussed, although, from our numerical results, the marginal estimators seem not to be sensitive to the bandwidth parameter. Finally, a Monte Carlo study is carried out to compare the performance of the robust proposed estimators among themselves and also with the classical ones, for normal and contaminated samples, under different missing data models. An example based on a real data set is also discussed.

There are no comments yet on this publication. Be the first to share your thoughts.