Skip to content

Task1 lpdid scaffold#343

Closed
wenddymacro wants to merge 13 commits into
igerber:mainfrom
wenddymacro:task1-lpdid-scaffold
Closed

Task1 lpdid scaffold#343
wenddymacro wants to merge 13 commits into
igerber:mainfrom
wenddymacro:task1-lpdid-scaffold

Conversation

@wenddymacro

@wenddymacro wenddymacro commented Apr 20, 2026

Copy link
Copy Markdown
Contributor

Methodology references (required if estimator / math changes)

  • Method name(s):
  • Paper / source link(s):
  • Any intentional deviations from the source (and why):

Validation

  • Tests added/updated:
  • Backtest / simulation / notebook evidence (if applicable):

Security / privacy

  • Confirm no secrets/PII in this PR:

wenddymacro and others added 13 commits March 18, 2026 14:04
@wenddymacro @claude
Add WooldridgeDiD (ETWFE) design spec
11e1b0a 
Design spec for integrating Stata jwdid (Wooldridge 2021/2023 ETWFE)
into diff-diff as a standalone WooldridgeDiD estimator with linear and
nonlinear support.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@wenddymacro
Merge branch 'main' of https://github.com/wenddymacro/diff-diff into …
ecadd06 
…main
@wenddymacro
feat: scaffold LPDiD estimator and results
cddbf46
@wenddymacro
fix: tighten LPDiD scaffold conventions
89735c3
@wenddymacro
fix: validate LPDiD params in set_params
761736c
@wenddymacro
feat: add lpdid fit validation contract
69bbabc
@wenddymacro
feat: add lpdid event and pooled result skeletons
05cfeb7
@wenddymacro
fix: include full lpdid pre horizons
5839d16
@wenddymacro
feat: estimate absorbing-path lpdid effects
e758f07
@wenddymacro
fix: harden lpdid task4 edge cases
f63c2c5
@wenddymacro
fix: fail fast on invalid lpdid pooled windows
644bff9
@wenddymacro
fix: align lpdid baseline estimation with stata
a800a35
@wenddymacro
feat: add LPDiD estimator with Stata parity coverage
0127447
@igerber igerber mentioned this pull request Jun 28, 2026
Merged
@igerber

igerber commented Jun 29, 2026

Copy link
Copy Markdown
Owner

Thank you, @wenddymacro, for this LP-DiD contribution — it's the foundation the new estimator was built on. 🙏

Your scaffold has grown into a full LPDiD (Local Projections Difference-in-Differences) estimator, which just landed in #575. We re-homed your engine spine — the clean-control sample construction and per-horizon long differences — and built it out to the library's standards: a finished LPDiDResults class, calendar-correct feature handling for unbalanced panels, clean-control support enforcement, cross-estimator equivalence + edge-case validation, and full docs.

Since #575 supersedes this branch (it was based on an older tree and carried a large data fixture), I'm closing this PR in its favor. The merged estimator credits your work in its description — thank you again for getting LP-DiD started in diff-diff!

@igerber igerber closed this Jun 29, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@wenddymacro @igerber