On model-free conditional coordinate tests for regressions

JOURNAL OF MULTIVARIATE ANALYSIS

卷:109

Article

Yu, Zhou¹ 

[1] E China Normal Univ, Sch Finance & Stat, Shanghai 200062, Peoples R China

关键词: Conditional coordinate test;    Sufficient dimension reduction;    Sliced inverse regression;   

DOI  :  10.1016/j.jmva.2012.02.004

来源: Elsevier

【 摘 要 】

Existing model-free tests of the conditional coordinate hypothesis in sufficient dimension reduction (Cook (1998) [3]) focused mainly on the first-order estimation methods such as the sliced inverse regression estimation (Li (1991) [14]). Such testing procedures based on quadratic inference functions are difficult to be extended to second-order sufficient dimension reduction methods such as the sliced average variance estimation (Cook and Weisberg (1991) [9]). In this article, we develop two new model-free tests of the conditional predictor hypothesis. Moreover, our proposed test statistics can be adapted to commonly used sufficient dimension reduction methods of eigendecomposition type. We derive the asymptotic null distributions of the two test statistics and conduct simulation studies to examine the performances of the tests. (C) 2012 Elsevier Inc. All rights reserved.

【 授权许可】

Free