文献速递流行病学与生物统计

平行整群随机试验中小样本校正方法控制I型错误的性能:模拟研究的系统综述

The performance of small sample correction methods for controlling type I error when analyzing parallel cluster randomized trials: a systematic review of simulation studies.
PubMed 文献 · J Clin Epidemiol · 2025-05-30

该系统综述检索了截至2024年8月30日的模拟研究,评估平行整群随机试验中小样本校正方法控制I型错误的性能。共纳入14项二分类结局研究和6项连续结局研究,发现部分校正方法在少至6个整群时可维持名义I型错误,但所有设置下保证名义I型错误需超过40个整群。

要点

  • 连续结局中,整群水平分析(t分布,组内-组间自由度)、线性混合模型(Satterthwaite校正)或广义估计方程(Fay and Graubard校正)在少至6个整群时多可维持名义I型错误。
  • 二分类结局中,未加权或逆方差加权整群水平分析可达到名义I型错误,但小整群或低患病率时可能反保守。
  • Kenward-Roger校正即使30个整群也偏保守;所有设置下保证名义I型错误需超过40个整群。

核心结论

  • 平行整群随机试验小样本校正文献复杂,现有校正可在极少整群时维持I型错误,但所有设置下保证名义I型错误需超过40个整群。

研究设计与样本

  • 系统综述检索Ovid Medline和Web of Science截至2024年8月30日的模拟研究,纳入评估小样本校正性能的研究。
  • 纳入二分类和连续结局,分析方法为广义线性混合模型、广义估计方程或整群水平方法;全文筛选和数据提取由两人独立重复完成。
  • 共纳入14项二分类结局研究和6项连续结局研究。

主要发现

  • 整群数范围为4至200;最小组内相关系数中位数0.001(范围0.000-0.200);最大组内相关系数0.10(范围0.05-0.70);最低患病率0.25(范围0.05-0.50);整群大小变异系数中位数1.00(范围0.80-1.50)。
  • 连续结局:整群水平分析(未加权或逆方差加权)配合t分布(组内-组间自由度)、线性混合模型配合Satterthwaite校正、或广义估计方程配合Fay and Graubard校正,在少至6个整群时多可维持名义I型错误(某些设置需至多40个整群)。
  • 连续结局:Kenward-Roger校正即使30个整群也偏保守。
  • 二分类结局:未加权或逆方差加权整群水平分析可达到名义I型错误,但小整群或低患病率时可能反保守;广义线性混合模型配合组内-组间校正少至10个整群可维持名义I型错误,但有时至多30个整群偏保守。
  • 二分类结局:Kenward-Roger或Satterthwaite校正更偏保守;广义估计方程中Mancl and DeRouen校正多可维持名义错误但可能反保守。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVES: Most cluster randomized trials (CRTs) include fewer than 50 clusters, yet the assumption of a "large sample" is relied upon to derive the sampling distributions of treatment effects. We review the current simulation study literature pertaining to small sample corrections for common analytical approaches for parallel CRTs. STUDY DESIGN AND SETTING: We searched Ovid Medline and Web of Science up to August 30 2024 for simulation studies evaluating the performance of small sample corrections. We include binary and continuous outcomes analyzed using generalized linear mixed models, generalized estimating equations, or cluster-level approaches. Full-text screening and data abstraction was performed independently in duplicate. RESULTS: Fourteen studies evaluated binary outcomes and 6 studies continuous outcomes. The number of clusters ranged from 4 to 200; the median smallest intracluster correlation coefficient was 0.001 [range 0.000-0.200]; largest intracluster correlation coefficient was 0.10 [range 0.05-0.70]; lowest prevalence was 0.25 [range 0.05-0.50]; and median coefficient of variation of cluster sizes 1.00 [range: 0.80-1.50]. For continuous outcomes, a cluster-level analysis (either unweighted or inverse-variance weighted) with a t-distribution (with between-within degree of freedom); a linear mixed model with a Satterthwaite correction; or a generalized estimating equation with the Fay and Graubard correction mostly preserve nominal type I error with as few as six clusters (although up to 40 clusters in some settings). Other approaches work less favorably (eg, Kenward-Roger is conservative even with 30 clusters). For binary outcomes, an unweighted or inverse-variance weighted cluster-level analysis can achieve nominal type I error (but can be anticonservative with small cluster sizes or low prevalence); as can a generalized linear mixed model with a between-within correction with as few as 10 clusters (but sometimes conservative with up to 30 clusters). Other corrections such as the Kenward-Roger or Satterthwaite correction are more conservative. For generalized estimating equations, the Mancl and DeRouen correction mostly seems to preserve nominal errors but can be anticonservative. CONCLUSION: The literature on the performance of small sample corrections for parallel CRTs is complex. While the available corrections can maintain type I error with a very small number of clusters, more than 40 clusters are required to guarantee nominal type I error across all settings.

来源:J Clin Epidemiol,查看原文。版权归原作者所有。

引用

  1. Hemming K, Thompson J, Kristunas C, et al. The performance of small sample correction methods for controlling type I error when analyzing parallel cluster randomized trials: a systematic review of simulation studies. J Clin Epidemiol. 2025. PMID: 40451478. doi:10.1016/j.jclinepi.2025.111838

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。