The propensity score is one of the most widely used tools in studying the causal effect of a treatment, intervention, or policy. Given that the propensity score is usually unknown, it has to be estimated, implying that the reliability of many treatment effect estimators depends on the correct specification of the (parametric) propensity score. This package implements the data-driven nonparametric diagnostic tools for detecting propensity score misspecification proposed by Sant'Anna and Song (2019) <doi:10.1016/j.jeconom.2019.02.002>.
| Version: | 0.1.3.900 |
| Depends: | R (≥ 3.1) |
| Imports: | stats, parallel, glmx, MASS, utils |
| Published: | 2019-08-26 |
| Author: | Pedro H. C. Sant'Anna, Xiaojun Song |
| Maintainer: | Pedro H. C. Sant'Anna <pedro.h.santanna at vanderbilt.edu> |
| License: | GPL-2 |
| URL: | https://github.com/pedrohcgs/pstest |
| NeedsCompilation: | no |
| Materials: | README |
| CRAN checks: | pstest results |
| Reference manual: | pstest.pdf |
| Package source: | pstest_0.1.3.900.tar.gz |
| Windows binaries: | r-devel: pstest_0.1.3.900.zip, r-release: pstest_0.1.3.900.zip, r-oldrel: pstest_0.1.3.900.zip |
| macOS binaries: | r-release: pstest_0.1.3.900.tgz, r-oldrel: pstest_0.1.3.900.tgz |
| Old sources: | pstest archive |
Please use the canonical form https://CRAN.R-project.org/package=pstest to link to this page.