BEGIN:VCALENDAR VERSION:2.0 PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4// BEGIN:VEVENT UID:20251214T060128EST-3585fuJaeR@132.216.98.100 DTSTAMP:20251214T110128Z DESCRIPTION:JOINT CORE/EBOH EPI Seminar Series Winter 2026\n\nThe Seminars in Epidemiology organized by the Department of Epidemiology\, Biostatistic s and Occupational Health at the 91Ë¿¹ÏÊÓƵ School of Population and Global He alth is a self-approved Group Learning Activity (Section 1) as defined by the maintenance of certification program of the Royal College of Physician s and Surgeons of Canada. Physicians requiring accreditation\, please comp lete the Evaluation Form and send to admincoord.eboh [at] mcgill.ca.\n\nPh ilippe Boileau\, PhD\n\nAssistant Professor of Biostatistics\n Department o f Epidemiology\, Biostatistics and Occupation Health\n 91Ë¿¹ÏÊÓƵ\n \nWHEN: Monday\, JANUARY 19\, 2026\, from 3:30-4:30pm\n WHERE: Hybrid | 200 1 91Ë¿¹ÏÊÓƵ College\, Rm 1140 &\n Onsite at 5252 boul. de Maisonneuve - 3rd fl oor\, 3B Kitchen | Zoom\n Note: Philippe Boileau will be presenting in-pers on at CORE\n\nAbstract\n\nThe conditional average treatment effect (CATE) is frequently estimated to refute the homogeneous treatment effect assumpt ion. Under this assumption\, all units making up the population under stud y experience identical benefit from a given treatment. Uncovering heteroge neous treatment effects through inference about the CATE\, however\, requi res that covariates truly modifying the treatment effect be reliably colle cted at baseline. CATE-based techniques will necessarily fail to detect vi olations when effect modifiers are omitted from the data due to\, for exam ple\, resource constraints. Severe measurement error has a similar impact. To address these limitations\, we prove that the homogeneous treatment ef fect assumption can be gauged through inference about contrasts of the pot ential outcomes’ variances. We derive causal machine learning estimators o f these contrasts and study their asymptotic properties. We establish that these estimators are doubly robust and asymptotically linear under mild c onditions\, permitting formal hypothesis testing about the homogeneous tre atment effect assumption even when effect modifiers are missing or mismeas ured. Numerical experiments demonstrate that these estimators’ asymptotic guarantees are approximately achieved in experimental and observational da ta alike. These inference procedures are then used to detect heterogeneous treatment effects in the re-analysis of randomized controlled trials inve stigating targeted temperature management in cardiac arrest patients.\n\nS peaker Bio\n\nPhilippe Boileau is an Assistant Professor of Biostatistics at 91Ë¿¹ÏÊÓƵ with a joint appointment in the Department of Epidemi ology\, Biostatistics and Occupational Health and the Department of Medici ne. He is also a Junior Scientist at the Research Institute of the 91Ë¿¹ÏÊÓƵ University Health Centre\, where he is the director of the Novel Trial Met hods Hub. Dr. Boileau is broadly interested in the development of assumpti on-lean statistical methods and their application to quantitative problems in the health and life sciences. Assumption-lean procedures combine causa l inference\, machine learning\, and semiparametric techniques to provide dependable statistical inference without relying on convenience assumption s. His most recent work has focused on developing and applying causal mach ine learning methods for heterogeneous treatment effect discovery in clini cal trial data.\n\nLearning Objectives\n\nAt the completion of this talk\, attendees will be able to:\n\n\n Describe limitations of existing statisti cal methods for heterogeneous treatment effect detection\;\n Interpret diff erential variance parameters\;\n Translate treatment effect homogeneity tes t results to clinical contexts.\n\n DTSTART:20260119T203000Z DTEND:20260119T213000Z SUMMARY:Assumption-Lean Differential Variance Inference for Heterogeneous T reatment Effect Detection URL:/spgh/channels/event/assumption-lean-differential- variance-inference-heterogeneous-treatment-effect-detection-369792 END:VEVENT END:VCALENDAR