
Bohrer Lecture: Dylan Small - Wharton, University of Pennsylvania

Talk Title: Exploration, Confirmation and Replication in the Same Observational Study
Talk Abstract: Exploratory data analysis, confirmatory data analysis and replication are three important aspects of building strong evidence from observational studies. Exploratory data analysis, confirmatory data analysis and replication are often thought of as being done on separate studies. However, for settings where randomized experiments are impossible to conduct for ethical reasons and observational studies must be relied on, it is common that there is a data set with unique strengths. We develop a two-team cross screening approach that allows for exploratory data analysis, confirmatory data analysis and replication to be done in the same observational study data set. We apply the approach to study the effect of unwanted pregnancy on mothers' later life outcomes using data from the Wisconsin Longitudinal Study. We will also briefly discuss data turnover, a one team cross-screening approach that provides some of the benefits of two-team cross screening with only one team. This is joint work with Samrat Roy, Marina Bogomolov, Ruth Heller, Amy Claridge, Tishra Beeson and Will Bekerman.