Photo credits
  • Chebyshev1983 - public domain
  • Suleiman.bako1982 - CC BY-SA 4.0
  • Iyusuf615 - CC BY-SA 4.0

Why these models

Methodology

The problem, the work this sits beside, and what this project does differently. Variable names, the model table and the estimating equations are on the Technical details page. Every number here is generated from the registry when the page is built.

1. The problem

Nigeria's public argument is usually about presidencies: did this administration improve health, reduce violence, grow the economy? The question is asked of five administrations and roughly twenty-seven years of annual national data. Four to five units against 22 to 23 observations per outcome cannot identify a per-president effect; the smallest detectable effect is tens of residual standard deviations.

This project asks what can be identified instead. It treats every outcome-and-design pair as its own model, publishes the number when a design earns one, and publishes the reason when it does not. 36 models are compared across 3 identification designs and 150 fitted specifications, 1999 to 2026.

2. What exists

Four strands of work bear directly on this one. The project uses their methods and inherits their warnings; the references are listed at the end with DOIs, checked against Crossref on 2026-10-28.

Synthetic control
Comparative case studies with a weighted donor pool, and the later statement of when the method is credible. Abadie & Gardeazabal (2003); Abadie, Diamond & Hainmueller (2010); Abadie (2021)
Panel designs and local projections
Staggered difference-in-differences, the decomposition of two-way fixed effects under variable timing, and local projections for shock transmission. Callaway & Sant'Anna (2021); Goodman-Bacon (2021); Jordà (2005)
Reporting the multiverse
Fit the grid, publish the distribution, and say which specification was preferred before seeing it. Simonsohn, Simmons & Nelson (2020); Athey & Imbens (2017)
Nigeria and the region
The resource-curse account of Nigeria's political economy, the greed-and-grievance account of civil war, and the micro evidence that democratisation reduced infant mortality in sub-Saharan Africa. Sala-i-Martin & Subramanian (2003); Collier & Hoeffler (2004); Kudamatsu (2012)

3. What this project does differently

The specification is written before the number
Every design lives in a committed spec file whose md5 the artifact records. Windows and verdict rules are read from those files at run time, not retyped.
Absence is a published output
Of 36 model cards, 2 carry a number and 34 carry a reason from a closed set. Thirty-four unexplained blanks cannot be mistaken for thirty-four null results.
Placebos decide, and the solver's choice is on the record
The synthetic control publishes its in-space and in-time placebos: 969 of 2,959 placebo fits clear the same pre-fit threshold, which is why it reports no identified effect. Because the weights are not unique with 99 donors, the artifact publishes the vertex and a ridge refit side by side.
Data honesty is drawn, not asserted
Of 4,008 outcome-months, 788 are observations; interpolated months are drawn dashed and tests run on the native grain. Every stage is re-derived by one of 23 independent verifiers in the chain.

4. What it does not claim

Where the numbers live

Everything the site shows was already computed into these committed files when the registry was built. No page renders by reading a database or refitting anything.

The detail, with the equations, the variables and the estimator tables, is on the technical page.

References

Bibliographic details checked against Crossref on 2026-10-28. DOIs are printed as text, not links: the site makes no network request, by design.

  1. Abadie, A., & Gardeazabal, J. (2003). The economic costs of conflict: A case study of the Basque Country. American Economic Review, 93(1), 113–132. https://doi.org/10.1257/000282803321455188
  2. Abadie, A., Diamond, A., & Hainmueller, J. (2010). Synthetic control methods for comparative case studies: Estimating the effect of California's tobacco control program. Journal of the American Statistical Association, 105(490), 493–505. https://doi.org/10.1198/jasa.2009.ap08746
  3. Abadie, A. (2021). Using synthetic controls: Feasibility, data requirements, and methodological aspects. Journal of Economic Literature, 59(2), 391–425. https://doi.org/10.1257/jel.20191450
  4. Callaway, B., & Sant'Anna, P. H. C. (2021). Difference-in-differences with multiple time periods. Journal of Econometrics, 225(2), 200–230. https://doi.org/10.1016/j.jeconom.2020.12.001
  5. Goodman-Bacon, A. (2021). Difference-in-differences with variation in treatment timing. Journal of Econometrics, 225(2), 254–277. https://doi.org/10.1016/j.jeconom.2021.03.014
  6. Jordà, Ò. (2005). Estimation and inference of impulse responses by local projections. American Economic Review, 95(1), 161–182. https://doi.org/10.1257/0002828053828518
  7. Simonsohn, U., Simmons, J. P., & Nelson, L. D. (2020). Specification curve analysis. Nature Human Behaviour, 4(11), 1208–1214. https://doi.org/10.1038/s41562-020-0912-z
  8. Athey, S., & Imbens, G. W. (2017). The state of applied econometrics: Causality and policy evaluation. Journal of Economic Perspectives, 31(2), 3–32. https://doi.org/10.1257/jep.31.2.3
  9. Sala-i-Martin, X., & Subramanian, A. (2003). Addressing the natural resource curse: An illustration from Nigeria (NBER Working Paper No. 9804). https://doi.org/10.3386/w9804
  10. Collier, P., & Hoeffler, A. (2004). Greed and grievance in civil war. Oxford Economic Papers, 56(4), 563–595. https://doi.org/10.1093/oep/gpf064
  11. Kudamatsu, M. (2012). Has democratization reduced infant mortality in sub-Saharan Africa? Evidence from micro data. Journal of the European Economic Association, 10(6), 1294–1317. https://doi.org/10.1111/j.1542-4774.2012.01092.x

Registry vintage 2026-11-01