MethodsGeneralizability of Subgroup EffectsSeamans, Marissa J.a; Hong, Hwanheeb; Ackerman, Benjaminc; Schmid, Iand; Stuart, Elizabeth A.c,d,eAuthor Information From the aDepartment of Epidemiology, Fielding School of Public Health, University of California, Los Angeles, CA bDepartment of Biostatistics and Bioinformatics, Duke University, Durham, NC cDepartment of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD dDepartment of Mental Health, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD eDepartment of Health Policy and Management, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD. Funding for this study was provided in part by the National Institutes of Health (T32DA007292 [PIs: Maher/Johnson], R00MH111807 [PI: Hong], P50MH115842 [PI: Daumit], T32MH109436 [PI: Barry/Stuart]) and the US Department of Education R305D150003 (PI: Stuart). The authors report no conflicts of interest. Supplemental digital content is available through direct URL citations in the HTML and PDF versions of this article (www.epidem.com). Code for the simulation presented in this article is available at https://github.com/MarissaSeamans/GeneralizabilitySubgroupEffects. Correspondence: Marissa J. Seamans, Department of Epidemiology, UCLA Fielding School of Public Health, 650 Charles E. Young Dr. S., Los Angeles, CA 90095. E-mail: [email protected]. Epidemiology: May 2021 - Volume 32 - Issue 3 - p 389-392 doi: 10.1097/EDE.0000000000001329 Buy SDC Metrics Abstract Generalizability methods are increasingly used to make inferences about the effect of interventions in target populations using a study sample. Most existing methods to generalize effects from sample to population rely on the assumption that subgroup-specific effects generalize directly. However, researchers may be concerned that in fact subgroup-specific effects differ between sample and population. In this brief report, we explore the generalizability of subgroup effects. First, we derive the bias in the sample average treatment effect estimator as an estimate of the population average treatment effect when subgroup effects in the sample do not directly generalize. Next, we present a Monte Carlo simulation to explore bias due to unmeasured heterogeneity of subgroup effects across sample and population. Finally, we examine the potential for bias in an illustrative data example. Understanding the generalizability of subgroup effects may lead to increased use of these methods for making externally valid inferences of treatment effects using a study sample. Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.