The standard static model of the effect of welfare program participation on labor
supply is estimated allowing the effect of participation to be heterogeneous in the
population and allowing the program participation decision to be endogenous and to
exhibit incomplete takeup. Nonparametric methods are used to estimate the
distribution of the marginal treatment effect over the range of participation rates
generated by the instruments, which are measures of the non-financial costs of
program participation. The results show that those with the greatest negative labor
supply effects of program participation enter first and, as participation expands,
individuals with smaller labor supply disincentives are drawn into the program.