A Cautionary Tale: Using Propensity Scores To Estimate the Effect of Food Stamps on Food Insecurity

We use propensity scores to evaluate the effect of Food Stamps on food insecurity, a measure of inadequate food supply. Data come from the Early Childhood Longitudinal Study–Kindergarten Cohort. Propensity scores offer an advantage over traditional linear regression methods because they address omitted variable bias associated with Food Stamp use by matching similarly situated treatment and control group members, and estimating mean differences within these matched groups. We find that the program does not decrease the probability of being food insecure, but it may lessen the severity of the problem. We also note that propensity scores rest on several stringent assumptions and should be employed with caution. A Cautionary Tale: Using Propensity Scores To Estimate the Effect of Food Stamps on Food Insecurity