David Card, Joshua Angrist, and Guido Imbens
Citation: For empirical contributions to labour economics (Card) and for methodological contributions to the analysis of causal relationships (Angrist and Imbens).
The key idea
Natural experiments — sudden policy changes, geographic discontinuities, lottery draws — allow recovery of causal effects without RCTs. Card's Mariel boatlift and minimum-wage studies; Angrist-Imbens's LATE framework and instrumental-variable revolution.
The explanation
Card's empirical strategy (with Alan Krueger) used the 1992 New Jersey minimum-wage hike as a natural experiment — and found, contrary to textbook prediction, no negative employment effect. Angrist-Imbens (1994) characterised the local-average-treatment effect (LATE) — what an IV regression actually estimates. The trio's work launched the credibility revolution in non-experimental empirical economics.
Why Africa should care
The natural-experiment toolkit is essential for African policy evaluation where RCTs aren't feasible. Kenya's free-primary-education rollout (2003) is a classic natural experiment. The Lewis-Land Reform discontinuity in Ethiopia, the partition of Sudan, monetary-union breakups (CEMAC vs EAC) all generate IV-type variation. African researchers can apply these methods at scale; many do.
How to use it
Before believing any cross-country or cross-region causal claim, ask: what variation is being exploited? If it's just observational variation, the claim is weak. If it's natural-experimental, the local-average-treatment-effect framework tells you what you've actually learned.
Canonical works
- David Card and Alan B. Krueger (1994) "Minimum Wages and Employment: A Case Study of the Fast-Food Industry in New Jersey and Pennsylvania" American Economic Review
- Joshua D. Angrist and Guido W. Imbens (1994) "Identification and Estimation of Local Average Treatment Effects" Econometrica
- Joshua D. Angrist and Jörn-Steffen Pischke (2009) "Mostly Harmless Econometrics: An Empiricist's Companion" Princeton University Press
More from Recent prizes · 2020-2025
- 2020Paul Milgrom and Robert Wilson
Auction design depends on what bidders know. Common-value auctions (the value is the same for all, but estimated differently) require different formats than private-value auctions. The FCC spectrum auctions are the canonical real-world success.
- 2022Ben Bernanke, Douglas Diamond, and Philip Dybvig
Banks are essential because they transform short-term deposits into long-term loans — but this maturity transformation makes them inherently fragile to runs (Diamond-Dybvig). The Great Depression became a catastrophe because the banking system failed (Bernanke).
- 2023Claudia Goldin
The gender pay gap in advanced economies is now primarily about flexibility and 'greedy' jobs — careers that reward long, unpredictable hours. The gap opens at parenthood, persists through career.
- 2024Daron Acemoglu, Simon Johnson, and James Robinson
Inclusive vs extractive institutions. Inclusive institutions (broad property rights, rule of law, political pluralism) produce sustained growth. Extractive institutions (elite-controlled, narrow rents) produce stagnation or boom-bust cycles. Colonial origins explain much of the modern institutional divergence.
- 2025Joel Mokyr, Philippe Aghion, and Peter Howitt
Mokyr: sustained growth requires both 'propositional knowledge' (why things work) and 'prescriptive knowledge' (how to do them). Aghion-Howitt: growth proceeds through Schumpeterian creative destruction — new innovations displace old, producing growth but also disruption.