pathintdid: Path-Integrated Difference-in-Differences
Implements the Path-Integrated Difference-in-Differences
('PI-DiD') framework of Salavi (2026), which treats the treatment
effect as a trajectory tau(t) = c1(t) - c0(t) and integrates the
baseline-differenced gap over a post-treatment window to obtain a
cumulative causal effect and a path-integrated average treatment
effect on the treated, together with cluster-robust standard errors,
confidence intervals, diagnostic plots, and the pre-treatment
parallel-trends, grid-density, and anticipation-robustness checks of
section 5 of the companion paper. This approach avoids the
endpoint-subtraction bias that arises whenever a transitory policy's
effect has fully decayed by the evaluation date, in which case the
conventional static difference-in-differences estimate can be zero
even though the cumulative benefit delivered to treated units was
strictly positive. Formerly distributed as a Stata package under the
names 'pidid' and 'pididplot'.
Documentation:
Downloads:
Linking:
Please use the canonical form
https://CRAN.R-project.org/package=pathintdid
to link to this page.