Division of Radiation Oncology, Department of Oncology, National Taiwan University Hospital, Taipei, Taiwan.
National Taiwan University Cancer Center, Taipei, Taiwan.
Res Synth Methods. 2019 Jun;10(2):255-266. doi: 10.1002/jrsm.1345. Epub 2019 Apr 3.
A systematic review and meta-analysis is an important step in evidence synthesis. The current paradigm for meta-analyses requires a presentation of the means under a random-effects model; however, a mean with a confidence interval provides an incomplete summary of the underlying heterogeneity in meta-analysis. Prediction intervals show the range of true effects in future studies and have been advocated to be regularly presented. Most commonly, prediction intervals are estimated assuming that the underlying heterogeneity follows a normal distribution, which is not necessarily appropriate. In this article, we provide a simple method with a ready-to-use spreadsheet file to estimate prediction intervals and predictive distributions nonparametrically. Simulation studies show that this new method can provide approximately unbiased estimates compared with the conventional method. We also illustrate the advantage and real-world significance of this approach with a meta-analysis evaluating the protective effect of vaccination against tuberculosis. The nonparametric predictive distribution provides more information about the shape of the underlying distribution than does the conventional method.
系统评价和荟萃分析是证据综合的重要步骤。目前荟萃分析的范式要求在随机效应模型下呈现均值；然而，均值及其置信区间并不能完全总结荟萃分析中的潜在异质性。预测区间显示了未来研究中真实效应的范围，并被主张定期呈现。最常见的是，预测区间是在假设潜在异质性遵循正态分布的情况下估计的，但这种假设不一定合适。在本文中，我们提供了一种简单的方法，并提供了一个现成的电子表格文件，以便非参数估计预测区间和预测分布。模拟研究表明，与传统方法相比，这种新方法可以提供近似无偏估计。我们还通过一项评估接种疫苗预防结核病的保护效果的荟萃分析说明了这种方法的优势和现实意义。非参数预测分布比传统方法提供了更多关于潜在分布形状的信息。
