期刊
AMERICAN JOURNAL OF EPIDEMIOLOGY
卷 191, 期 9, 页码 1640-1651出版社
OXFORD UNIV PRESS INC
DOI: 10.1093/aje/kwac087
关键词
bounds; inverse probability of treatment weighting; propensity score truncation
资金
- Food and Drug Administration [75F40119C10155]
Inverse probability weighting (IPW) and targeted maximum likelihood estimation (TMLE) are methodologies for adjusting confounding and selection bias, with the former requiring finite inverse probability weights and the latter needing bounded propensity scores. A truncation strategy proposed by the authors optimizes the mean squared error of the parameter estimate based on sample size, demonstrating the ability to minimize bias and mean squared error compared to other common strategies.
Inverse probability weighting (IPW) and targeted maximum likelihood estimation (TMLE) are methodologies that can adjust for confounding and selection bias and are often used for causal inference. Both estimators rely on the positivity assumption that within strata of confounders there is a positive probability of receiving treatment at all levels under consideration. Practical applications of IPW require finite inverse probability (IP) weights. TMLE requires that propensity scores (PS) be bounded away from 0 and 1. Although truncation can improve variance and finite sample bias, this artificial distortion of the IP weights and PS distribution introduces asymptotic bias. As sample size grows, truncation-induced bias eventually swamps variance, rendering nominal confidence interval coverage and hypothesis tests invalid. We present a simple truncation strategy based on the sample size, n, that sets the upper bound on IP weights at root n In n/5. For TMLE, the lower bound on the PS should be set to 5/(root n ln n/5). Our strategy was designed to optimize the mean squared error of the parameter estimate. It naturally extends to data structures with missing outcomes. Simulation studies and a data analysis demonstrate our strategy's ability to minimize both bias and mean squared error in comparison with other common strategies, including the popular but flawed quantile-based heuristic.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据