Provides functions to conduct robust inference in difference-in-differences and event study designs by implementing the methods developed in Rambachan & Roth (2023) <doi:10.1093/restud/rdad018>, "A More Credible Approach to Parallel Trends" [Previously titled "An Honest Approach..."]. Inference is conducted under a weaker version of the parallel trends assumption. Uniformly valid confidence sets are constructed based upon conditional confidence sets, fixed-length confidence sets and hybridized confidence sets.
| Version: |
0.2.6 |
| Depends: |
R (≥ 3.6.0) |
| Imports: |
stats, rlang, foreach (≥ 1.4.7), matrixStats (≥ 0.63.0), CVXR (≥ 0.99-6), latex2exp (≥ 0.4.0), lpSolveAPI (≥
5.5.2.0-17), Matrix (≥ 1.2-17), pracma (≥ 2.2.5), purrr (≥
0.3.4), tibble (≥ 1.3.4), dplyr (≥ 0.7.4), ggplot2 (≥
2.2.1), Rglpk (≥ 0.6-4), mvtnorm (≥ 1.1-3), TruncatedNormal (≥ 1.0) |
| Suggests: |
knitr, testthat, haven, lfe, rmarkdown |
| Published: |
2024-07-14 |
| DOI: |
10.32614/CRAN.package.HonestDiD |
| Author: |
Ashesh Rambachan [aut, cph, cre],
Jonathan Roth [aut, cph] |
| Maintainer: |
Ashesh Rambachan <ashesh.a.rambachan at gmail.com> |
| License: |
MIT + file LICENSE |
| NeedsCompilation: |
no |
| CRAN checks: |
HonestDiD results |