Estimation and Inference for Heckman Selection Models with Cluster-Robust Variance.
heckmanGE 
heckmanGE
The heckmanGE package has functions for modeling data with selection bias problems. It includes the generalized Heckman model, introduced by Bastos, Barreto-Souza, and Genton (2022), which allows the inclusion of covariates to the dispersion and correlation parameters, allowing the sample selection bias and the dispersion parameters to depend on covariates. More than that, our package allows the inclusion of sample weights and the grouping of data into clusters, in such a way that between clusters the errors are independent, but correlated within each cluster. The package also allows the adjustment of the classical Heckman model (Heckman (1976), Heckman (1979)) and the estimation of the parameters of this model via the maximum likelihood method and the two-step method.
Installation
You can install the released version of heckmanGE from CRAN with:
install.packages("heckmanGE")
And the development version from GitHub with:
# install.packages("devtools")
devtools::install_github("fsbmat-ufv/heckmanGE")
Code of Conduct
{heckmanGE} is released with a Contributor Code of Conduct.
References
Bastos, Fernando de Souza, Wagner Barreto-Souza, and Marc G Genton. 2022. “A Generalized Heckman Model with Varying Sample Selection Bias and Dispersion Parameters.” Statistica Sinica.
Heckman, James J. 1976. “The Common Structure of Statistical Models of Truncation, Sample Selection and Limited Dependent Variables and a Simple Estimator for Such Models.” In Annals of Economic and Social Measurement, Volume 5, Number 4, 475–92. NBER.
———. 1979. “Sample Selection Bias as a Specification Error.” Econometrica: Journal of the Econometric Society, 153–61.