Difference In Differences
2 articles
Cycling Through Bad Ideas Faster: A Medicaid Branding Worked Example
A staggered Callaway-Sant'Anna DiD on state Medicaid branding. A naive +22% headline collapses to a bounded null once expansion-cohort × year fixed effects absorb confounded timing.
Understanding the Limits of Parallel Trends Tests
Why a high p-value on parallel trends tests can mislead, and how sensitivity analysis reveals fragile causal claims.