Working Paper, Socioeconomic Institute, University of Zurich 0314
I consider the problem of evaluating the effect of a health care reform on the demand for doctor visits when the effect is potentially different in different parts of the outcome distribution. Quantile regression is a useful technique for studying such heterogeneous treatment effects. Recent progree has been made to extend such methods to applications with a count dependent variable. An analysis of a 1997 health care reform in Germany shows the benefit of the approach: lower quantiles, such as the 25 percent quantile, fell by substantially larger amounts than what would have been predicted based on Poisson or negative binomial models.
heterogeneous treatment effect count data quantile regression Poisson model