全球智库信息集成服务系统

Using observational data from the Education Longitudinal Survey of 2002, the effect of coaching on the SAT is estimated via linear regression and propensity score matching approaches. The key features of taking a propensity score matching approach to support causal inferences are highlighted relative to the more traditional linear regression approach. A central difference is that propensity score matching restricts the sample from which effects are estimated to coached and uncoached students that are considered comparable. For those students that have taken both the PSAT and SAT, effect estimates of roughly 11 to 15 points on the math section and 6 to 9 points on the verbal are found. Only the math effects are statistically significant. Evidence is found that coaching is more effective for certain kinds of students, particularly those who have taken challenging academic coursework and come from high socioeconomic backgrounds. In the present empirical context the summary causal inference being drawn does not depend much upon whether the effect is estimated using linear regression or propensity score matching.