Fall Seminar Series  October 8, 2009
University of Minnesota
School of Statistics
College
of Liberal Arts

Automatic Model Structure Selection for Partially Linear Models

Hao Helen Zhang
Department of Statistics
  North Carolina State University

Thursday, October 8, 2009
3:30 PM, 115 Ford Hall
Minneapolis, East Bank Campus
Social at 3:00 PM, 300 Ford Hall

 

Abstract

Partial linear models provide good compromises between linear and nonparametric models. However, how to decide which covariates are linear and which are nonlinear is a long-standing problem and not completely solved yet. Two methods are commonly used in practice: the first method is based on hypotheses testing, which is theoretically challenging due to multiple nonparametric tests. The second method is preliminary screening based on univariate analysis such as scatter plots to decide the proper regression form for each term, which is kind of very ad hoc. In this paper, we tackle this problem in the model selection perspective. A unified estimation and selection approach is proposed, and it can automatically determine the linearity or nonlinearity of each covariate and estimate these components consistently at the same time. Both theoretical and numerical properties of the proposed estimators are presented.