infonet-economy

The bivariate probit model is frequently used for estimating the eff*ect of an endogenous binary regressor (the "treatment") on a binary health outcome variable. This paper discusses simple modifi*cations that maintain the probit assumption for the marginal distributions while introducing non-normal dependence using copulas. In an application of the copula bivariate probit model to the effect of insurance status on the absence of ambulatory health care expenditure, a model based on the Frank copula outperforms the standard bivariate probit model.