I present four new commands to estimate the effect of a binary endogenous treatment on an ordered outcome. Such models conventionally rely upon joint normality of the unobservables in treatment and outcome processes, as do treatoprobit and switchoprobit. In this article, I highlight the capabilities of treatoprobitsim and switchoprobitsim, which both use a latent-factor structure to model the joint distribution of the treatment and outcome and allow the researcher to relax the assumption of joint normality.
AakvikA., HeckmanJ. J., and VytlacilE. J.2005. Estimating treatment effects for discrete outcomes when responses to treatment vary: An application to Norwegian vocational rehabilitation programs. Journal of Econometrics125: 15–51.
DebP., and TrivediP. K.2006a. Maximum simulated likelihood estimation of a negative binomial regression model with multinomial endogenous treatment. Stata Journal6: 246–255.
4.
DebP., and TrivediP. K.2006b. Specification and simulated likelihood estimation of a non-normal treatment-outcome model with selection: Application to health care utilization. Econometrics Journal9: 307–331.
5.
DrukkerD. M., and GatesR.2006. Generating Halton sequences using Mata. Stata Journal6: 214–228.
6.
GreeneW. H., and HensherD. A.2010. Modeling Ordered Choices: A Primer.Cambridge: Cambridge University Press.
7.
MirandaA., and Rabe-HeskethS.2006. Maximum likelihood estimation of endogenous switching and sample selection models for binary, ordinal, and count variables. Stata Journal6: 285–308.
8.
TrainK. E.2009. Discrete Choice Methods with Simulation. 2nd ed. Cambridge: Cambridge University Press.
