A Mallows-Type Model Averaging Estimator for the Varying-Coefficient Partially Linear Model

• 成果类型: Article
• 署名作者: Zhu, Rong; Wan, Alan T. K.; Zhang, Xinyu; Zou, Guohua
• 署名单位: Chinese Academy of Sciences; Academy of Mathematics & System Sciences, CAS; Chinese Academy of Sciences; University of Chinese Academy of Sciences, CAS; City University of Hong Kong; Capital Normal University
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.1080/01621459.2018.1456936
• 发表日期: 2019
• 页码: 882-892
• 关键词: focused information criteria; efficient estimation; quantile regression; selection; inference

摘要

In the last decade, significant theoretical advances have been made in the area of frequentist model averaging (FMA); however, the majority of this work has emphasized parametric model setups. This article considers FMA for the semiparametric varying-coefficient partially linear model (VCPLM), which has gained prominence to become an extensively used modeling tool in recent years. Within this context, we develop a Mallows-type criterion for assigning model weights and prove its asymptotic optimality. A simulation study and a real data analysis demonstrate that the FMA estimator that arises from this criterion is vastly preferred to information criterion score-based model selection and averaging estimators. Our analysis is complicated by the fact that the VCPLM is subject to uncertainty arising not only from the choice of covariates, but also whether the covariate should enter the parametric or nonparametric parts of the model. Supplementary materials for this article are available online.