Merged
Conversation
Extend the library to optionally work across multiple time periods: - Add MultiPeriodDiD estimator that handles multiple pre/post periods - Add MultiPeriodDiDResults for period-specific and average ATT - Add PeriodEffect dataclass for individual period treatment effects - Support for period dummies and treatment × period interactions - Compute average ATT with proper covariance-adjusted standard errors - Allow custom reference period selection - Auto-infer post-periods when not specified (last half of periods) - Full support for covariates, fixed effects, and absorbed FE - Cluster-robust and heteroskedasticity-robust standard errors - Comprehensive test suite with 28 new tests (70 total passing)
igerber
pushed a commit
that referenced
this pull request
Jan 4, 2026
igerber
added a commit
that referenced
this pull request
Apr 18, 2026
Addresses axis B findings #6 and #7 from the silent-failures audit: trop_global.py:448 outer alternating-min loop, trop_global.py:466 hard-coded range(20) inner FISTA loop, and trop_local.py:680 alternating-minimization loop all exited silently on max_iter exhaustion, returning the current iterate as if converged. - trop_global._solve_global_with_lowrank: thread a converged flag through the outer loop; count non-convergence events from the inner FISTA and surface the count in the outer warning for diagnostic context. One warn_if_not_converged call per solver invocation. - trop_local._estimate_model: thread a converged flag through the outer alternating-min loop; call warn_if_not_converged on exhaustion. - REGISTRY updated under TROP. New TestTROPConvergenceWarnings class (4 tests) exercises both global and local paths with forced non-convergence (max_iter=1, tol=1e-15) and a convergent negative control. Notable: the default TROP local config (max_iter=100, tol=1e-6) does not converge within max_iter on typical synthetic panels, so this PR surfaces a previously silent non-convergence that affected routine user fits. No numerical change in the returned iterate; the warning is additive. Axis-B regression-lint baseline: 5 -> 2 silent range(max_iter) loops remaining (minor loops in honest_did/power not yet addressed). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
igerber
added a commit
that referenced
this pull request
Apr 19, 2026
P0: bias_corrected_local_linear now routes the CI through `safe_inference()` so degenerate cases with `se_robust <= 0` or non-finite `se_robust` (e.g., exact-fit / constant-y) return `(NaN, NaN)` rather than a misleading zero-width or infinite CI. Matches the repo-wide inference contract (CLAUDE.md Key Design Pattern #6). P1: Auto-bandwidth path now calls `lpbwselect_mse_dpi` directly with `cluster`, `vce`, and `nnmatch` forwarded. Previously it went through `mse_optimal_bandwidth` which hard-codes unclustered / nn / nnmatch=3, silently mismatching the downstream `lprobust` fit's reported estimator. Tests added: TestNaNSafeCI (constant-y + near-zero-SE) and TestAutoBandwidthForwardsParameters (cluster+auto, vce='hc1'+auto, nnmatch=5+auto), all asserting the selected bandwidth changes when the corresponding parameter changes (catches silent fallback). Also: suppress spurious BLAS FPE warnings in lprobust_bw's hc/hc2/hc3 branch (numpy issue #21432 pattern), newly reachable via the wired-through vce='hc1' auto-bandwidth path. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
igerber
added a commit
that referenced
this pull request
Apr 22, 2026
Close BR/DR gap #6: target-parameter block in schemas
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Extend the library to optionally work across multiple time periods: