An Evaluation of Instrumental Variable Strategies for Estimating the Effects of Catholic Schooling (WP-02-29)
Joseph Altonji, Todd Elder, and Christopher Taber
Several previous studies have relied on religious affiliation and the proximity to Catholic schools as exogenous sources of variation for identifying the effect of Catholic schooling on a wide variety of outcomes. Using three separate methodologies, we examine the validity of these instrumental variables. We find that none of the candidate instruments is a useful source of identification of the Catholic school effect, at least in currently available data sets. In particular, two stage least square procedures using Catholic religion or proximity as an instrument imply implausibly large positive effects for high school graduation and college attendance rates, but each of the evaluation methods imply biases of similar magnitudes to the 2SLS coefficients themselves. In these situations, with both 2SLS estimates and potential biases being very large, instrumental variables methods may not contribute any new information beyond that gained from single-equation estimates.