Abstract
ssc install drdid, replace
DRDID implements Sant'Anna and Zhao (2020) proposed estimators for the Average Treatment Effect on the Treated (ATT) in Difference-in-Differences (DID) setups where the parallel trends assumption holds after conditioning on a vector of pre-treatment covariates. For a generalization to multiple periods see CSDID. The main estimators in DRDID are locally efficient and doubly-robust estimators, because they combine Inverse probability weighting and outcome regression to estimate ATT's. DRDID can be applied to both balanced/unbalanced panel data, or repeated cross-section.
DRDID implements Sant'Anna and Zhao (2020) proposed estimators for the Average Treatment Effect on the Treated (ATT) in Difference-in-Differences (DID) setups where the parallel trends assumption holds after conditioning on a vector of pre-treatment covariates. For a generalization to multiple periods see CSDID. The main estimators in DRDID are locally efficient and doubly-robust estimators, because they combine Inverse probability weighting and outcome regression to estimate ATT's. DRDID can be applied to both balanced/unbalanced panel data, or repeated cross-section.
Original language | English |
---|---|
Publication status | Published - 5 Aug 2021 |
Austrian Classification of Fields of Science and Technology (ÖFOS)
- 102009 Computer simulation
- 502042 Environmental economics
- 502025 Econometrics
- 502022 Sustainable economics