期刊
MEDICAL DECISION MAKING
卷 34, 期 7, 页码 911-918出版社
SAGE PUBLICATIONS INC
DOI: 10.1177/0272989X14545789
关键词
randomized controlled trials; network meta-analysis; mixed treatments comparisons; generalized linear mixed models
资金
- National Science Council in Taiwan [NSC 101-2314-B-002-197-MY2]
In the past decade, a new statistical method-network meta-analysis-has been developed to address limitations in traditional pairwise meta-analysis. Network meta-analysis incorporates all available evidence into a general statistical framework for comparisons of multiple treatments. Bayesian network meta-analysis, as proposed by Lu and Ades, also known as mixed treatments comparisons, provides a flexible modeling framework to take into account complexity in the data structure. This article shows how to implement the Lu and Ades model in the frequentist generalized linear mixed model. Two examples are provided to demonstrate how centering the covariates for random effects estimation within each trial can yield correct estimation of random effects. Moreover, under the correct specification for random effects estimation, the dummy coding and contrast basic parameter coding schemes will yield the same results. It is straightforward to incorporate covariates, such as moderators and con-founders, into the generalized linear mixed model to conduct meta-regression for multiple treatment comparisons. Moreover, this approach may be extended easily to other types of outcome variables, such as continuous, counts, and multinomial.
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