Empirical Likelihood Inference for Partially Linear Models

• Activity Number: 558
• Type: Contributed
• Date/Time: Wednesday, August 12, 2015 : 10:30 AM to 12:20 PM
• Sponsor: International Chinese Statistical Association
• Author(s): Haiyan Su*
• Companies: Montclair State University
• Keywords: empirical likelihood ; partially linear models

Abstract

We propose an empirical likelihood (EL)-based inference for the linear component coefficient in partially linear models and partially linear mixed-effect models. The proposed method combines the projection method with the EL method. The project method is used to remove the nuisance parameter in the model and then EL method is used to construct confidence intervals for the linear component. Bartlett correction method is used to correct the EL-based confidence intervals. The test statistic is shown to follow regular chi-square distribution asymptotically. The numerical performance of the method under normal and non-normal error terms is evaluated through simulation studies.