Are Experiments the Only Option? A Look at Dropout Prevention Programs
Explores whether propensity score methods produce unbiased estimates of program impacts, by comparing experimental and propensity score impacts of dropout prevention programs. Finds no consistent evidence that they do--even when the data available for matching are extensive. Suggests that evaluators who plan to use these types of methods must scrutinize how programs recruit individuals and why individuals enter programs, since unobserved factors may exert powerful influences on outcomes.