Using the Linear Probability Model to Estimate Impacts on Binary Outcomes in Randomized Controlled Trials
In this brief we examine methodological criticisms of the Linear Probability Model (LPM) in general and conclude that these criticisms are not relevant to experimental impact analysis. We also point out that the LPM has advantages in terms of implementation and interpretation that make it an appealing option for researchers conducting experimental impact analysis. An important caveat on these conclusions is that outside of the context of impact analysis, there can be good reasons to avoid using the LPM for binary outcomes.
Teen Pregnancy Prevention: Ensuring Rigorous Program Evaluations
U.S. Department of Health and Human Services, Administration for Children and Families, Family & Youth Services Bureau