Graphical criteria enable formal covariate selection for conditional parallel trends in DiD, revealing conflicts with unconditional assumptions, useful roles for time-invariant covariates, and misalignment issues in popular estimators.
A New Approach to Causal Inference in Mortality Studies with a Sustained Exposure Period—Application to Control of the Healthy Worker Survivor Effect
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A formal approach to variable selection in difference-in-differences
Graphical criteria enable formal covariate selection for conditional parallel trends in DiD, revealing conflicts with unconditional assumptions, useful roles for time-invariant covariates, and misalignment issues in popular estimators.