Pharmacoepidemiology and Pharmacoeconomics, Brigham and Women's Hospital and Harvard Medical School, Boston, Massachusetts.
The Arthritis Research UK Epidemiology Unit, University of Manchester, Manchester, UK.
Pharmacoepidemiol Drug Saf. 2019 Oct;28(10):1290-1298. doi: 10.1002/pds.4846. Epub 2019 Aug 5.
In nonexperimental comparative effectiveness research, restricting analysis to subjects with better overlap of covariate distributions, hence greater treatment equipoise, helps balance the groups compared and can improve validity. Three alternative approaches, derived from different perspectives, implement restriction by trimming observations in the tails of the propensity score (PS). Across approaches, we compared the relationships between the overlap in treatment-specific PS distributions and the size of the balanced study population after trimming.
The three trimming approaches considered were absolute trimming to the range 0.1<PS<0.9, asymmetric trimming to include subjects in both treatment groups with PS above the 5th percentile of the distribution in the target group and below the 95th percentile in the comparison group, and restriction to preference score values between 0.3 and 0.7. Comparisons of approaches used simulated PSs from beta distributions and two example studies.
The magnitude of the C-statistic strongly predicted (R ≥.95) the percent of the balanced study population remaining. The balanced study population was largest under trimming at absolute PS levels, unless the target treatment was uncommon. Fewer than half of original study subjects remained after preference score trimming if C≥.80 and after asymmetric trimming if C≥.85. In examples, trimming improved the precision of estimated risk differences and identified apparent treatment effect heterogeneity in the PS tails where covariate balance was limited. Relative amounts of trimming in examples reflected the simulation results.
Study populations with high PS C-statistics include only small percentages of subjects in whom valid treatment effects are confidently expected.
在非实验性比较效果研究中，限制分析对象具有更好的协变量分布重叠，从而实现更好的治疗均衡，有助于平衡比较组并提高有效性。有三种源自不同视角的替代方法，通过修剪倾向评分（PS）尾部的观察值来实施限制。在所有方法中，我们比较了处理特定 PS 分布重叠与修剪后平衡研究人群大小之间的关系。
考虑的三种修剪方法是绝对修剪到 0.1<PS<0.9 的范围、不对称修剪，包括 PS 高于目标组分布第 5 百分位且低于比较组第 95 百分位的两组治疗中的受试者，以及限制在偏好评分值在 0.3 到 0.7 之间。方法比较使用来自 beta 分布的模拟 PS 和两个示例研究。
C 统计量的大小强烈预测（R≥.95）了平衡研究人群的剩余百分比。在修剪绝对 PS 水平下，平衡研究人群最大，除非目标治疗不太常见。如果 C≥.80，则在偏好评分修剪后，原始研究对象中不到一半的对象保留下来；如果 C≥.85，则在不对称修剪后不到一半的对象保留下来。在示例中，修剪提高了估计风险差异的精度，并在协变量平衡有限的 PS 尾部识别出明显的治疗效果异质性。示例中的修剪量相对反映了模拟结果。
具有高 PS C 统计量的研究人群仅包括很小比例的可以有信心预期有效治疗效果的对象。
