Estimating the Associations between SNAP and Food Insecurity,Obesity, and Food Purchases with Imperfect Administrative Measures of Participation

Administrative data are considered the “gold standard” when measuring program participation, but little evidence exists on their potential problems or implications for econometric estimates. We explore these issues using the FoodAPS, a unique data set containing two different administrative measures of Supplemental Nutrition Assistance Program (SNAP) participation and a survey‐based measure. We document substantial ambiguity in the two administrative measures and show that they disagree with each other almost as often as they disagree with self‐reported participation. Estimated participation and misreporting rates can be meaningfully sensitive to choices made to resolve this ambiguity and disagreement. We explore sensitivity in regression estimates of the associations between SNAP and food insecurity, obesity, and the healthy eating index. The signs are unchanged across the three measures, and the estimates are mostly not statistically different from each other. However, there are some meaningful differences in the magnitudes and levels of statistical significance of the estimates.