期刊
JOURNAL OF THE NEUROLOGICAL SCIENCES
卷 285, 期 1-2, 页码 206-211出版社
ELSEVIER
DOI: 10.1016/j.jns.2009.07.017
关键词
Poisson regression; Negative binomial regression; Cox proportional hazards model; Over-dispersion; Count data; Log-link function
Patients with multiple sclerosis (MS) often experience unpredictable recurrent relapses with periods of remission. The modeling of MS relapse data is complicated because both within-subject serial dependence between relapses and between-patient heterogeneity may exist. We compare six statistical methods for assessing the treatment efficacy in reducing the frequency of relapses in MS clinical trials. All methods can be implemented in SAS (R), and are grouped into two classes, one based on Poisson-type regressions for count data and the other on Cox proportional hazards models for time to relapse. We apply these models to the data of a Tysabri (R) (Natalizumab) MS trial and interpret the differences in results based on the underlying assumptions. Negative binomial regression is recommended for evaluating the overall treatment effect because of its simplicity and efficiency. (c) 2009 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据