March 21, 2024 Webinar
Target Trial Emulation for Evaluating Health Policy
Nicholas Seewald, PhD
Abstract:
Target trial emulation is an approach to designing rigorous non-experimental studies by "emulating" key features of a clinical trial. Most commonly used outside policy contexts, this approach is also valuable for policy evaluation as policies typically are not randomly assigned. I discuss how to apply the target trial emulation framework in a policy evaluation context, with examples from a study investigating the effects of state medical cannabis laws on opioid and guideline-concordant non-opioid prescribing for chronic noncancer pain treatment among commercially-insured U.S. adults. The policy trial emulation framework includes the following 7 components: the exposure, the scientific question and estimand, the units, baseline ("time zero"), the treatment assignment procedure, the outcomes, and the analysis strategy. Policy evaluations that emulate a randomized trial across these dimensions can yield estimates of the causal effects of the policy on outcomes. Using the policy trial emulation framework to conduct and report on research design and methods supports transparent assessment of threats to causal inference in non-experimental studies intended to assess the effect of a health policy on clinical or population health outcomes.
Short Bio:
Nick Seewald is an Assistant Professor in the Department of Biostatistics, Epidemiology and Informatics in the Perelman School of Medicine at the University of Pennsylvania. Dr. Seewald's methodological research is primarily related to causal inference using complex repeated measures data, using both experimental and non-experimental approaches. He has particular expertise in difference-in-differences and sequentially-randomized trials. His work is motivated by problems across a wide array of applications, including oncology, substance use and related policy, chronic disease, and mobile health. He is deeply interested in building tools to address important statistical issues in a way that is accessible and understandable to applied researchers.