Skip to content

Tags: igerber/diff-diff

Tags

v3.8.0

Toggle v3.8.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Bump version to 3.8.0 (#693)

Release the work merged to main since v3.7.0: the RegressionDiscontinuity
estimator (alias RDD) — sharp, fuzzy, and covariate-adjusted local-polynomial
RD with robust bias-corrected inference, parity-targeting R rdrobust 4.0.0
end-to-end (all 10 bandwidth selectors, three kernels, mass-points, fuzzy Wald
ratio via treatment_col=, additive covariate adjustment via covariates=, with
guarded degenerate-design handling documented as deviations from R) — plus the
internal enforcement of mypy at zero errors across the package.

Converts the curated [Unreleased] CHANGELOG section to [3.8.0] - 2026-07-18 and
syncs the version string across __init__.py, pyproject.toml, rust/Cargo.toml,
llms-full.txt, and CITATION.cff (date-released 2026-07-18).


Claude-Session: https://claude.ai/code/session_01Y4H4R5iy4iXxnZrgixs6Bs

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

v3.7.0

Toggle v3.7.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Bump version to 3.7.0 (#661)

Release the work merged to main since v3.6.2 (41 commits): the ContinuousDiD
capability push (covariate support, discrete-treatment saturated regression,
lowest-dose-as-control), the systematic Callaway/staggered standard-error
parity sweep vs canonical R backed by the se-audit test locks, EfficientDiD
and Callaway performance work (incl. Rust batched-Cholesky and HC2 kernels),
imputation leave-one-out variance, and the completed removal of the
deprecated HAD survey=/weights= kwargs across all 8 surfaces.

Converts the curated [Unreleased] CHANGELOG section to [3.7.0] - 2026-07-08
(leading with the Removed breaking change) and syncs the version string
across __init__.py, pyproject.toml, rust/Cargo.toml, llms-full.txt, and
CITATION.cff.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

v3.6.2

Toggle v3.6.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Bump version to 3.6.2 (#609)

v3.6.1

Toggle v3.6.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Bump version to 3.6.1 (#593)

Release 3.6.1. Changes since 3.6.0:
- LPDiD non-absorbing (reversible) treatment with entry-effect estimands
  (Dube, Girardi, Jorda & Taylor 2025) + complex-survey-design support
  (survey_design=), each R-parity validated.
- TROP non-absorbing (on/off) treatment support, opt-in local method
  (Athey, Imbens, Qu & Viviano 2025).
- Weighted multiple absorbed fixed effects (absorb=[a, b, ...]) via
  iterative alternating-projection demeaning.
- CallawaySantAnna materializes non-estimable (g,t) cells as NaN.
- Fix: BusinessReport appendix render failures now surfaced.
- R-parity validation backfill for the LPDiD absorbing/non-absorbing/survey
  paths; survey zero-weight-PSU SE-invariance item waived (Lumley
  full-design convention); SciPy lower-bound doc alignment.

Promotes the CHANGELOG [Unreleased] section to [3.6.1] - 2026-07-01 and
syncs the version across __init__.py, pyproject.toml, rust/Cargo.toml,
llms-full.txt, and CITATION.cff.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

v3.6.0

Toggle v3.6.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Bump version to 3.6.0 (#581)

Release 3.6.0. Highlights since 3.5.3:
- New estimator: LPDiD (Local Projections DiD; Dube, Girardi, Jorda &
  Taylor 2025), exported from the top-level package with full API docs.
- PlaceboTests: new optional `treatment` param on placebo_group_test,
  fake-group path now filters ever-treated by default, and
  permutation_test reports the (1+count)/(B+1) randomization-inference
  p-value.
- ~78-84% peak-memory reduction in the multiplier-bootstrap estimators
  (Callaway-Sant'Anna, EfficientDiD, HeterogeneousAdoptionDiD) via
  block-tiled weight generation.
- Methodology validation promoted to Complete: TwoStageDiD, PlaceboTests,
  Survey Data Support.
- Security: pyo3 + numpy 0.28 -> 0.29 (RUSTSEC-2026-0176/0177); deps and
  CI hardening (blas-src, checkout v7, release-build guard).
- Numerous perf and rank-deficiency correctness fixes across linalg,
  imputation, two-stage, conley, spillover, and continuous DiD.

Promotes the CHANGELOG [Unreleased] section to [3.6.0] - 2026-06-29 and
syncs the version across __init__.py, pyproject.toml, rust/Cargo.toml,
llms-full.txt, and CITATION.cff.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

v3.5.3

Toggle v3.5.3's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #547 from igerber/release/3.5.3

Release v3.5.3

v3.5.2

Toggle v3.5.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #536 from igerber/release/3.5.2

Release v3.5.2: version bump + CHANGELOG reconciliation

v3.5.1

Toggle v3.5.1's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #526 from igerber/release/3.5.1

v3.5.0

Toggle v3.5.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #516 from igerber/release/3.5.0

Bump version to 3.5.0

v3.4.2

Toggle v3.4.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #494 from igerber/release/3.4.2

Bump version to 3.4.2