Specification and simulated likelihood estimation of a non-normal treatment-outcome model with selection: Application to health care utilization

We develop a specification and estimation framework for a class of nonlinear, non-normal microeconometric models of treatment and outcome with selection. A latent factor structure is used to accommodate selection into treatment and a simulated likelihood method is used for estimation. The methodology is applied to examine the causal effect of managed care, a multinomial discrete choice process, on the utilization of health care services, measured as binary indicators and counts. The results indicate that there are significant unobserved self-selection effects and these effects substantially change the estimated effects of insurance on utilization.