More Than Numbers: The Power of Graphs in Meta-Analysis
More Than Numbers: The Power of Graphs in Meta-Analysis
复制标题
DOI：
10.1093/aje/kwn340
复制
发表时间：
2009-01-15
影响因子：
5
通讯作者：
Moons, Karel G. M.
中科院分区：
文献类型：
--
作者：
Bax, Leon;Ikeda, Noriaki;Moons, Karel G. M.
在Meta分析中，对图表的评估被广泛用于识别或排除异质性和发表偏差。为此，有多种图表可供选择。然而，到目前为止，还没有对这些图表的性能进行比较评估。为了评估图表评分的重复性和有效性，作者模拟了来自4个情景的100个荟萃分析，涵盖了有和没有异质性和发表偏见的情况。从每个Meta分析中，作者产生了11种类型的图表(盒子图、加权盒子图、标准化残差直方图、正态分位数图、森林图、3种漏斗图、修剪填充图、加尔布雷思图和L的阿贝图)，3位评价者对所得的1,100张图进行了评估。量表重复性的组内相关系数从差(ICC=0.34)到高(ICC=0.91)不等。森林样地的等级和标准化残差直方图与参数异质性的相关性最好。图表评级和出版偏见(研究审查)之间的关联性很差。元分析师应该在选择图表时有所选择，以探索他们的数据。
In meta-analysis, the assessment of graphs is widely used in an attempt to identify or rule out heterogeneity and publication bias. A variety of graphs are available for this purpose. To date, however, there has been no comparative evaluation of the performance of these graphs. With the objective of assessing the reproducibility and validity of graph ratings, the authors simulated 100 meta-analyses from 4 scenarios that covered situations with and without heterogeneity and publication bias. From each meta-analysis, the authors produced 11 types of graphs (box plot, weighted box plot, standardized residual histogram, normal quantile plot, forest plot, 3 kinds of funnel plots, trim-and-fill plot, Galbraith plot, and L'Abbe plot), and 3 reviewers assessed the resulting 1,100 plots. The intraclass correlation coefficients (ICCs) for reproducibility of the graph ratings ranged from poor (ICC = 0.34) to high (ICC = 0.91). Ratings of the forest plot and the standardized residual histogram were best associated with parameter heterogeneity. Association between graph ratings and publication bias (censorship of studies) was poor. Meta-analysts should be selective in the graphs they choose for the exploration of their data.