An analysis of transformations for additive nonparametric regression

• 成果类型: Article
• 署名作者: Linton, OB; Chen, R; Wang, NS; Hardle, W
• 署名单位: Yale University; Texas A&M University System; Texas A&M University College Station; Humboldt University of Berlin
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.2307/2965422
• 发表日期: 1997
• 页码: 1512-1521
• 关键词: kernel estimation; models; identification

摘要

We consider a nonparametric regression model with a parametric family of dependent variable transformations, one of which induces additive covariate effects. We estimate the additive regression effects using the integration method and estimate the transformation parameter from a profiled instrumental variable and pseudolikelihood criterion. The asymptotic distributions of the parameter and regression estimates are given. The practical performance is investigated via an application.