aer-identification

AER Identification

Overview

In AER-track empirical economics, identification is the paper. This skill routes among canonical designs, modern defaults, and referee-facing diagnostics.

If the design is fragile, return to aer-topic-selection; writing cannot save it.

When to Use

• Designing the empirical strategy for a new project
• The current strategy is TWFE / first-stage F / naive RDD and the referee will flag it
• A prior submission was rejected on identification grounds and the design needs rebuilding
• Choosing between two candidate identification strategies for the same question

Master Decision Tree

Is treatment assignment plausibly random conditional on observables?
├── Yes, by design (RCT, lottery) → run the RCT analysis; register PAP via AEA RCT Registry
└── No → identification must come from variation
    ├── Sharp threshold in a running variable → RDD (sharp or fuzzy)
    ├── Discrete policy change in some units, not others, over time → DiD
    │     ├── Single treatment date → canonical 2×2 DiD
    │     └── Staggered adoption → Callaway-Sant'Anna or Borusyak-Jaravel-Spiess
    ├── Endogenous regressor + plausibly exogenous shifter → IV
    │     ├── Shifter × pre-existing exposure shares → shift-share / Bartik
    │     └── Single instrument → weak-IV-robust inference if F < 50
    ├── One treated unit / aggregate intervention → synthetic control
    └── None of the above → reconsider the question

Difference-in-Differences

Canonical 2×2 (single treatment date, two groups)

Use TWFE if and only if:

• Treatment timing is simultaneous for all treated units
• The control group is never treated
• Treatment-effect heterogeneity is implausible

Otherwise, TWFE produces biased and often sign-flipped estimates.

Staggered Adoption (most modern applications)

Do not use TWFE. Use one of:

• Callaway and Sant'Anna (2021) — csdid (Stata), did (R). Identifies group-time average treatment effects (ATT(g,t)); estimands are doubly robust; supports event-study aggregation.
• Borusyak, Jaravel, and Spiess (2024) — imputation estimator.
• de Chaisemartin and D'Haultfœuille (2020) — did_multiplegt.
• Sun and Abraham (2021) — interaction-weighted estimator for event studies.