摘要
当样本量较小时,渐近检验方法通常表现不佳.针对小样本的分层双边数据,在Donner模型下对不同层中的相对风险比进行精确检验.基于Score检验提出小样本下的两种精确方法,即E方法和M方法.拟合结果表明E方法在第一类错误率和功效上表现较优.
Asymptotic methods have usually poor performance when sample size is small.For small samples in stratified bilateral data,the paper proposes exact tests of relative risk ratio under Donner’s model.Based on score test,two exact methods are introduced in small samples such as E and M methods.Simulations show E method performs better in terms of empirical type I error rate and power.
作者
牟珂漪
李智明
MOU Keyi;LI Zhiming(School of Mathematics and System Sciences,Xinjiang University,Urumqi Xinjiang 830017,China)
出处
《新疆大学学报(自然科学版)(中英文)》
CAS
2022年第3期293-299,330,共8页
Journal of Xinjiang University(Natural Science Edition in Chinese and English)
基金
国家自然科学基金项目(12061070)
新疆维吾尔自治区自然科学基金项目(2021D01E13,2018Q011).