Learning about a target population by combining information from multiple sources

Department of Epidemiology Seminar Series

Speaker:

Issa Dahabreh, MD, ScD
Associate Professor, Department of Epidemiology
Harvard T.H. Chan School of Public Health

Abstract:

In recent years there has been increasing interest in analyses that combine data from multiple sources to estimate some causal, predictive, or descriptive parameter of interest. Examples of such work involve “transportability” analyses that estimate causal effects in a target population by combining data from a completed randomized trial and a separately obtained sample from the target population; tailoring of prediction models to a target population in which outcomes cannot be ascertained (and related work on covariate shift / domain adaptation); causally interpretable meta-analysis; and various other “data-fusion” activities. Using the example of causally interpretable meta-analysis, we examine the interplay between causal assumptions, study design, and sampling properties when learning by combining information from multiple sources.

Open to the public.