Package: did2s 1.1.0

Kyle Butts

did2s: Two-Stage Difference-in-Differences Following Gardner (2021)

Estimates Two-way Fixed Effects difference-in-differences/event-study models using the approach proposed by Gardner (2021) <doi:10.48550/arXiv.2207.05943>. To avoid the problems caused by OLS estimation of the Two-way Fixed Effects model, this function first estimates the fixed effects and covariates using untreated observations and then in a second stage, estimates the treatment effects.

Authors:Kyle Butts [aut, cre], John Gardner [aut], Grant McDermott [ctb], Laurent Berge [ctb]

did2s_1.1.0.tar.gz
did2s_1.1.0.zip(r-4.5)did2s_1.1.0.zip(r-4.4)did2s_1.1.0.zip(r-4.3)
did2s_1.1.0.tgz(r-4.5-any)did2s_1.1.0.tgz(r-4.4-any)did2s_1.1.0.tgz(r-4.3-any)
did2s_1.1.0.tar.gz(r-4.5-noble)did2s_1.1.0.tar.gz(r-4.4-noble)
did2s_1.1.0.tgz(r-4.4-emscripten)did2s_1.1.0.tgz(r-4.3-emscripten)
did2s.pdf |did2s.html✨
did2s/json (API)
NEWS

# Install 'did2s' in R:

install.packages('did2s', repos = c('https://kylebutts.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/kylebutts/did2s/issues

Pkgdown site:https://kylebutts.github.io

Datasets:

castle - Data from Cheng and Hoekstra
df_het - Simulated data with two treatment groups and heterogenous effects
df_hom - Simulated data with two treatment groups and homogenous effects

On CRAN:

7.89 score 96 stars 134 scripts 717 downloads 7 exports 125 dependencies

Last updated 3 months agofrom:bb8be20038. Checks:1 OK, 7 NOTE. Indexed: yes.

Target	Result	Latest binary
Doc / Vignettes	OK	Feb 08 2025
R-4.5-win	NOTE	Feb 08 2025
R-4.5-mac	NOTE	Feb 08 2025
R-4.5-linux	NOTE	Feb 08 2025
R-4.4-win	NOTE	Feb 08 2025
R-4.4-mac	NOTE	Feb 08 2025
R-4.3-win	NOTE	Feb 08 2025
R-4.3-mac	NOTE	Feb 08 2025

Exports:did2s event_study gen_data get_honestdid_obj_did2s honest_did_did2s plot_event_study sparse_model_matrix

Dependencies:abind backports BH bigmemory bigmemory.sri BMisc boot broom car carData caret class cli clock codetools colorspace corrplot cowplot cpp11 data.table Deriv diagram did didimputation digest doBy dplyr DRDID dreamerr e1071 fansi farver fastglm fixest foreach Formula future future.apply generics ggplot2 ggpubr ggrepel ggsci ggsignif globals glue gower gridExtra gtable hardhat ipred isoband iterators KernSmooth labeling lattice lava lifecycle listenv lme4 lubridate magrittr MASS Matrix MatrixModels mgcv microbenchmark minqa ModelMetrics modelr munsell nlme nloptr nnet numDeriv parallelly pbapply pbkrtest pillar pkgconfig plyr polynom pROC prodlim progressr proxy purrr quantreg R6 rbibutils RColorBrewer Rcpp RcppArmadillo RcppEigen Rdpack recipes reformulas reshape2 rlang rpart rstatix sandwich scales shape SparseM sparsevctrs SQUAREM staggered stringi stringmagic stringr survival tibble tidyr tidyselect timechange timeDate trust tzdb utf8 uuid vctrs viridisLite withr zoo

Two-Stage Difference-in-Differences

Rendered fromTwo-Stage-Difference-in-Differences.Rmdusingknitr::rmarkdownon Feb 08 2025.

Last update: 2024-06-21
Started: 2021-06-02

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Data from Cheng and Hoekstra (2013)	castle
Simulated data with two treatment groups and heterogenous effects	df_het
Simulated data with two treatment groups and homogenous effects	df_hom
Calculate two-stage difference-in-differences following Gardner (2021)	did2s
Estimate event-study coefficients using TWFE and 5 proposed improvements.	event_study plot_event_study
Generate TWFE data	gen_data
get_honestdid_obj_did2s	get_honestdid_obj_did2s
honest_did_did2s	honest_did_did2s
Design matrix of a 'fixest' object returned in sparse format	sparse_model_matrix