A Local Projections Approach to Difference-in-Differences Event Studies /
Dube, Arindrajit.
A Local Projections Approach to Difference-in-Differences Event Studies / Arindrajit Dube, Daniele Girardi, Òscar Jordà, Alan M. Taylor. - Cambridge, Mass. National Bureau of Economic Research 2023. - 1 online resource: illustrations (black and white); - NBER working paper series no. w31184 . - Working Paper Series (National Bureau of Economic Research) no. w31184. .
April 2023.
We propose a local projection (LP) based difference-in-differences approach that subsumes many of the recent solutions proposed in the literature to address possible biases arising from negative weighting. We combine LPs with a flexible 'clean control' condition to define appropriate sets of treated and control units. Our proposed LP-DiD estimator can be implemented with various weighting and normalization schemes for different target estimands, accommodates controls for pre-treatment values of the outcome and of other time-varying covariates, and is simple and fast to implement. Simulations and two empirical applications demonstrate that the LP-DiD estimator performs well in common applied settings.
System requirements: Adobe [Acrobat] Reader required for PDF files.
Mode of access: World Wide Web.
Econometric and Statistical Methods and Methodology: General
Panel Data Models • Spatio-temporal Models
Econometric Modeling
A Local Projections Approach to Difference-in-Differences Event Studies / Arindrajit Dube, Daniele Girardi, Òscar Jordà, Alan M. Taylor. - Cambridge, Mass. National Bureau of Economic Research 2023. - 1 online resource: illustrations (black and white); - NBER working paper series no. w31184 . - Working Paper Series (National Bureau of Economic Research) no. w31184. .
April 2023.
We propose a local projection (LP) based difference-in-differences approach that subsumes many of the recent solutions proposed in the literature to address possible biases arising from negative weighting. We combine LPs with a flexible 'clean control' condition to define appropriate sets of treated and control units. Our proposed LP-DiD estimator can be implemented with various weighting and normalization schemes for different target estimands, accommodates controls for pre-treatment values of the outcome and of other time-varying covariates, and is simple and fast to implement. Simulations and two empirical applications demonstrate that the LP-DiD estimator performs well in common applied settings.
System requirements: Adobe [Acrobat] Reader required for PDF files.
Mode of access: World Wide Web.
Econometric and Statistical Methods and Methodology: General
Panel Data Models • Spatio-temporal Models
Econometric Modeling