wber-identification

• SKILL.mdcore · 8,566 bytes

# Identification Strategy (wber-identification)

## When to trigger

- A causal claim rests on OLS + controls, or TWFE on staggered reform timing
- An RCT's estimand, balance, attrition, or spillover handling is not pinned down
- An RD's density, bandwidth, or covariate-smoothness defense is missing
- An IV's first stage is weak or the exclusion restriction is asserted, not argued
- The design is clean but the *policy interpretation* (scale-up, GE, fiscal cost) is missing

## The WBER identification bar

WBER demands the **same identification rigor as a top applied-micro field journal** — and then one more thing that siblings let slide: the **mapping from the local causal estimate to a development-policy lesson** must be argued, not assumed. A pristine ITT from one trial is necessary but not sufficient; the WBER referee asks "what does this imply for a finance ministry deciding whether to scale this?" So state the estimand, name the identifying assumption, show the diagnostic that could have failed, **and** address external validity, general equilibrium, and scaling. Inference must match the design (clustering at the assignment level; few-cluster corrections). Report standard errors and confidence intervals — not significance asterisks.