Modeling SSA's sequential disability determination process using matched SIPP data.

Abstract

We model the Social Security Administration's (SSA's) disability determination process using household survey information exact matched to SSA administrative information on disability determinations. Survey information on health, activity limitations, demographic traits, and work are taken from the Survey of Income and Program Participation (SIPP). We estimate a multistage sequential logit model, reflecting the structure of the determination procedure used by State Disability Determination Services agencies. The findings suggest that the explanatory power of particular variables can be appropriately ascertained only if they are introduced at the relevant stage of the determination process. Hence, as might be expected by those familiar with the process, medical variables and activity limitations are major factors in the early stages of the process, while past work, age, and education play roles in later stages. The highly detailed administrative information on outcomes at each stage allows clarification of the roles of particular variables. Planned future work will include policy estimates, such as the number of persons in the general population eligible for the disability programs, as well as analysis of applications behavior in a household context.