关于两总体均值差的一种半参数假设检验方法

A semiparametric hypothesis testing method on the difference of two population means

近年来,已有一些在半参数密度函数比模型下建立半参数统计分析方法的报道,这些方法往往比参数方法稳健,比非参数方法有效.在本文里,我们提出一种半参数的假设检验方法用于对两总体均值差进行假设检验.该方法主要建立在对两总体均值差进行半参数估计的基础上.我们报告了一些理论和统计模拟的结果,得出该方法在数据符合正态性假设时,比常用的参数和非参数方法略好;而在数据不符合正态性假设时,它的优势就非常明显.我们还将提出的方法用到了两组真实数据的分析上.

In the literature, some semiparametric statistical methods were recently developed under density ratio models, and these methods are usually more robust than parametric methods and more effective than nonpara- metric methods. In this paper, we propose a semiparametric hypothesis testing method on the difference of two population means under a semiparametric density ratio model. This method is essentially built upon semipara- metric estimation of the difference of two population means. Some theoretical results as well as simulation results are provided, which suggest that our proposed method is slightly superior to some commonly used parametric and nonparametric methods when data are normal, and is significantly better than them when data are not normal, We also apply our proposed method to analysis to two real examples.