|国家预印本平台
首页|基于渐进和重抽样二项分布的等价性检验

基于渐进和重抽样二项分布的等价性检验

esting the equality of several independent binomial proportions based on asymptotic and resampling method

中文摘要英文摘要

本文讨论了k(k>2)个独立二项分布比例的等价性检验问题。主要讨论了似然比,Socre和Wald统计量在MaxT,MinP和Step-down方法下的第一类错误的概率。在不同的参数设置下,上述统计量的表现较好,经验结果显示MaxT和MinP方法第一类错误接近于指定的显著性水平。本文最后给出一个例子证实本文结论。

his paper discusses equality test of proportions in k (k≥2) independent binomial distributions on the basis of likelihood-ratio, score and Wald-type statistics via asymptotic, MaxT, MinP and Step-down methods. The performance of these test statistics are investigated with respect to the type I error rates and powers under various settings of parameters. Empirical results show that MaxT and MinP methods behave satisfactorily in the sense that their type I error rates are close to the pre-specified nominal level. An example is used to illustrate the proposed methodologies.

李杰、邓丽君

数学

蒙特卡洛Bootstrap方法似然比检验Score检验Wald检验二项分布

Monte Carlo methodBootstrap methodLikelihood testScore testWald testBinomial distribution

李杰,邓丽君.基于渐进和重抽样二项分布的等价性检验[EB/OL].(2011-04-13)[2025-08-19].http://www.paper.edu.cn/releasepaper/content/201104-288.点此复制

评论