Compact reference object for the Sequeira (2016) application reported in Table 4 of Sant'Anna and Xu (2026). It contains the paper-final Table 4 estimates, stationarity-test p-values, and local-polynomial nuisance fitted values and bandwidths from the original application output. The object lets users verify the published DR DiD rows without depending on the historical replication repository or rerunning the multi-hour cross-validation step.
Format
A list with five components:
- description
Short description of the reference.
- table4
Data frame with estimator labels, outcomes, estimates, standard errors, and clustered standard errors.
- tests
Data frame with the stationarity-test statistic, unclustered p-value, and clustered bootstrap p-value.
- locpol
Local-polynomial nuisance fits, bandwidths, variables, seed, and bootstrap draw count used by the paper-final application run.
- provenance
Source hashes and source-audit notes.
Source
Paper-final output files from the Sequeira application archived in
the project Dropbox folder and mirrored in
pedrohcgs/DiD_Compositional_Changes.
References
Sequeira, S. (2016). Corruption, trade costs, and gains from tariff liberalization: Evidence from Southern Africa. American Economic Review, 106(10), 3029-3063.
Sant'Anna, P. H. C., and Xu, Q. (2026). Difference-in-Differences with compositional changes. Journal of Econometrics, 253, 106147.