DiD replication — original collection
22 original studies · 1,338 plotted comparisons.
The original collection is credited to Peter Hull. These 22 papers follow the selection criteria established in his twfe-replication repository, accompanying Two-Way Fixed Effects and Modern Difference-in-Differences: An Empirical Comparison. We preserve the original collection in full as the reference, with its available archived results.
Each report distinguishes source-replication checks from additional estimator comparisons. The community extension, potential refinements and provisional eligibility assessments are kept separately under Under development; they do not redefine the original collection or Peter Hull’s criteria.
Original comparisons: JSON · CSV · Membership totals · Code · Editable template
Studies
| Study | Status | Report |
|---|---|---|
| Curriculum and Ideology | 660 comparison summaries | Report |
| Do Powerful Politicians Really Cause Corporate Downsizing? | 73 comparison summaries | Report |
| Reply: Do Powerful Politicians Really Cause Corporate Downsizing? | 72 comparison summaries | Report |
| Market Integration Demand and the Growth of Firms | 49 comparison summaries | Report |
| Do Government Audits Reduce Corruption? | 21 comparison summaries | Report |
| Railroads of the Raj | 4 comparison summaries | Report |
| The Arrival of Fast Internet and Employment in Africa | 4 comparison summaries | Report |
| Copyrights and Creativity | 33 comparison summaries | Report |
| Vertical Integration Supplier Behavior and Quality Upgrading | 29 comparison summaries | Report |
| Leadership in Social Movements | 4 comparison summaries | Report |
| Hall of Mirrors | 4 comparison summaries | Report |
| The Rise and Fall of Local Elections in China | 8 comparison summaries | Report |
| Ideology and Performance in Public Organizations | 15 comparison summaries | Report |
| Reconciliation Narratives | 28 comparison summaries | Report |
| Retail Pharmacies and Drug Diversion | 10 comparison summaries | Report |
| The Gift of a Lifetime | 60 comparison summaries | Report |
| Trading Nontradables | 10 comparison summaries | Report |
| The Rise of Fiscal Capacity | 69 comparison summaries | Report |
| The Real State | Comparison unavailable | Report |
| Credit Markets Property Rights and the Commons | 9 comparison summaries | Report |
| Landmines and Spatial Development | 16 comparison summaries | Report |
| Corruption as a Local Advantage | 173 comparison summaries | Report |
Calibration comparisons
Both axes use the matching TWFE standard error: x = TWFE / SE(TWFE), y = alternative estimate / SE(TWFE). Colors identify studies; circles denote static specifications and squares denote event-study averages. Capped points are marked at the boundary. Use the range selector or hover for actual coordinates and specification details.
BJS and Sun–Abraham use outline rings for cohort-homogeneity rejection at 5%, from the homoskedastic deviations F-test without multiplicity adjustment. Missing tests are not non-rejections. CS-DID has separate equal-event-time and treated-cell summaries. Multisynth results remain in paper reports and downloads, not separate calibration panels.
Sign reversals: 7.4%. Homogeneity rejected: 52/253 available tests. Downloads use the capped view; hover shows actual values.
Sign reversals: 18.1%. Homogeneity rejected: 52/253 available tests. Downloads use the capped view; hover shows actual values.
Sign reversals: 16.3%. No homogeneity-test annotations. Aggregation and donor information are in the tooltip. Downloads use the capped view; hover shows actual values.
Sign reversals: 15.8%. No homogeneity-test annotations. Aggregation and donor information are in the tooltip. Downloads use the capped view; hover shows actual values.
Sign reversals: 15.2%. No homogeneity-test annotations. Aggregation and donor information are in the tooltip. Downloads use the capped view; hover shows actual values.
Sign reversals: 8.8%. No homogeneity-test annotations. Aggregation and donor information are in the tooltip. Downloads use the capped view; hover shows actual values.
Sign reversals: 27.9%. No homogeneity-test annotations. Aggregation and donor information are in the tooltip. Downloads use the capped view; hover shows actual values.
Library extension
The Under development tab is a community effort to extend and potentially refine these analyses. It holds the additional papers, extension plots and downloads, contributor acknowledgments and provisional eligibility log.