Apples and Oranges: Comparing the Backgrounds and Academic Trajectories of International Baccalaureate (IB) Students to a Matched Comparison Group

As a critical step in understanding the impacts of IB, the analyses presented in this report examined the selection mechanisms behind IB participation across Florida, the state with the second highest representation of IB programs in the nation. We use longitudinal student and school-level data from 1995 through 2009 from the Florida K-20 Education Data Warehouse (EDW) to characterize individual students' educational histories from elementary school through high school and into college. To address issues of selection bias, we use propensity score methods (Rosenbaum & Rubin, 1983) to adjust for preexisting differences between IB and non-IB students. These analyses are designed to address the following research questions: (1) What are the student- and school-level predictors of participating in the IB Diploma Programme in Florida?; (2) To what degree does propensity score stratification or matching reduce selection bias associated with key student and school-level factors?; (3) What are the estimated differences in key postsecondary access indicators (i.e., SAT and ACT scores) and enrollment statistics (e.g., college selectivity) with and without different types of propensity score adjustments? Results revealed that, when looking at the statewide population in Florida, the selection bias associated with voluntary participation in IB is very large, and that mechanisms for dealing with selection bias using propensity scores may not be sufficient.