A note on overadjustment in inverse probability weighted estimation

• 成果类型: Article
• 署名作者: Rotnitzky, Andrea; Li, Lingling; Li, Xiaochun
• 署名单位: Universidad Torcuato Di Tella; Harvard University; Harvard Medical School; Harvard Pilgrim Health Care; Indiana University System; Indiana University Bloomington; Regenstrief Institute Inc
• 刊物名称: BIOMETRIKA
• ISSN/ISSBN: 0006-3444
• DOI: 10.1093/biomet/asq049
• 发表日期: 2010
• 页码: 9971001
• 关键词: adjustment

摘要

Standardized means, commonly used in observational studies in epidemiology to adjust for potential confounders, are equal to inverse probability weighted means with inverse weights equal to the empirical propensity scores. More refined standardization corresponds with empirical propensity scores computed under more flexible models. Unnecessary standardization induces efficiency loss. However, according to the theory of inverse probability weighted estimation, propensity scores estimated under more flexible models induce improvement in the precision of inverse probability weighted means. This apparent contradiction is clarified by explicitly stating the assumptions under which the improvement in precision is attained.