Assessing Heterogeneity of Treatment E ↵ects in Observational Studies.

We describe methods for assessing heterogeneity of treatment e↵ects over pre-specified subgroups in observational studies, using outcome model-based (g-formula), inverse probability weighting, doubly robust, and matching estimators of subgroup-specific potential outcome means, conditional average treatment e↵ects, and measures of het- erogeneity of treatment e↵ects. We compare the finite-sample performance of di↵erent estimators in simulation studies where we vary the total sample size, the relative fre- quency of each subgroup, the magnitude of treatment e↵ect in each subgroup, and the distribution of baseline covariates, for both continuous and binary outcomes. We find that the estimators' bias and variance vary substantially in finite samples, even when there is no unobserved confounding and no model misspecification. As an illustration, we apply the methods to data from the Coronary Artery Surgery Study to compare the e↵ect of surgery plus medical therapy versus medical therapy alone for chronic coronary artery disease in subgroups defined by previous myocardial infarction or left ventricular ejection fraction. PMID: 33083822 [PubMed - as supplied by publisher]
Source: Am J Epidemiol - Category: Epidemiology Authors: Tags: Am J Epidemiol Source Type: research