CMStatistics 2021: Start Registration
View Submission - CMStatistics
Title: Causal inference when resources are constrained Authors:  Mats Stensrud - Ecole polytechnique federale de Lausanne (Switzerland) [presenting]
Abstract: Many treatments are of limited supply and cannot be provided to all individuals in need. For example, many hospitals have experienced shortages of ventilators, protective equipment and personnel during the COVID-19 pandemic. Similarly, there are waiting lists for organ transplants in most health care systems because suitable organs constitute a limited resource. When resources are limited, policymakers often raise questions about the effects of allocation strategies where only a limited proportion of individuals receive treatment at a given time. We will present current work on causal estimands that target such questions. We will emphasize why existing causal inference methods cannot be used, and we will also give new identifiability results and suggest new estimators.