SNAP is designed to reduce food insecurity – reduced food intake or disrupted eating patterns in a household due to lack of money or other resources – but data quantifying this effect is limited. The objectives of this study were to: Assess how food security and food expenditures vary with SNAP participation. Examine how relationships between SNAP and food security and between SNAP and food expenditures vary by household characteristics and circumstances. Estimating the effect of SNAP on food insecurity using household survey data is challenging because households that choose to participate in SNAP can differ in systematic ways from households that do not participate, making it hard to distinguish the impact of SNAP from these other factors. This study sought to control for the SNAP participation “selection bias” by comparing information collected from households within days of entering the program (new entrants) to information obtained after about 6 months of participation.