RDHonest: Honest Inference in Regression Discontinuity Designs

Honest and nearly-optimal confidence intervals in fuzzy and sharp regression discontinuity designs and for inference at a point based on local linear regression. The implementation is based on Armstrong and Kolesár (2018) <doi:10.3982/ECTA14434>, and Kolesár and Rothe (2018) <doi:10.1257/aer.20160945>. Supports covariates, clustering, and weighting.

Version: 1.0.0
Depends: R (≥ 4.3.0)
Imports: stats, Formula, withr
Suggests: spelling, ggplot2, testthat, knitr, rmarkdown, formatR
Published: 2024-03-22
Author: Michal Kolesár ORCID iD [aut, cre, cph], Tim Armstrong [ctb]
Maintainer: Michal Kolesár <kolesarmi at googlemail.com>
BugReports: https://github.com/kolesarm/RDHonest/issues
License: GPL-3
URL: https://github.com/kolesarm/RDHonest
NeedsCompilation: no
Language: en-US
Materials: NEWS
CRAN checks: RDHonest results

Documentation:

Reference manual: RDHonest.pdf
Vignettes: RDHonest

Downloads:

Package source: RDHonest_1.0.0.tar.gz
Windows binaries: r-devel: RDHonest_1.0.0.zip, r-release: RDHonest_1.0.0.zip, r-oldrel: RDHonest_1.0.0.zip
macOS binaries: r-release (arm64): RDHonest_1.0.0.tgz, r-oldrel (arm64): RDHonest_1.0.0.tgz, r-release (x86_64): RDHonest_1.0.0.tgz, r-oldrel (x86_64): RDHonest_1.0.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=RDHonest to link to this page.