Methods for Analysis of Pre-Post Data in Clinical Research: A Comparisonof Five Common Methods

Journal of Biometrics & Biostatistics

article

Nathaniel S. O'Connell¹  Lin Dai¹  Yunyun Jiang¹  Jaime L. Speiser¹  Ralph Ward¹  Wei Wei¹  Rachel Carroll¹  Mulugeta Gebregziabher¹ 

[1] Department of Public Health Sciences, Medical University of South Carolina

关键词: Analysis of variance;    Analysis of covariance;    Linear mixed model;    Pre-post;    Rrandomized trial;    Repeated measures;   

DOI  :  10.4172/2155-6180.1000334

来源: Hilaris Publisher

【 摘 要 】

Often repeated measures data are summarized into pre-post-treatment measurements. Various methods exist in the literature for estimating and testing treatment effect, including ANOVA, analysis of covariance (ANCOVA), and linear mixed modeling (LMM). Under the first two methods, outcomes can either be modeled as the post treatment measurement (ANOVA-POST or ANCOVA-POST), or a change score between pre and post measurements (ANOVACHANGE, ANCOVA-CHANGE). In LMM, the outcome is modeled as a vector of responses with or without Kenward- Rogers adjustment. We consider five methods common in the literature, and discuss them in terms of supporting simulations and theoretical derivations of variance. Consistent with existing literature, our results demonstrate that each method leads to unbiased treatment effect estimates, and based on precision of estimates, 95% coverage probability, and power, ANCOVA modeling of either change scores or post-treatment score as the outcome, prove to be the most effective. We further demonstrate each method in terms of a real data example to exemplify comparisons in real clinical context.

【 授权许可】

Unknown