Fix HC2 and HC2-BM finite variances at leverage one

TODO.md

@@ -22,7 +22,6 @@ Related tracking surfaces:
 | Issue | Location | Origin | Effort | Priority |
 |-------|----------|--------|--------|----------|
 | Consolidate the remaining estimator-entangled DR/logit score variants (`staggered.py::_doubly_robust` + RC twins, `triple_diff.py`, `lwdid.py`, `wooldridge.py`) onto the shared `_dr_scores.py` module, each migration with its own committed oracle capture (the ContinuousDiD lift's two-tier pattern in `tests/test_dr_scores.py`); and add a ridge vcov path to `solve_ridge` if an estimator ever needs analytical ridge inference | `diff_diff/_dr_scores.py` | dml-b0 | Mid | Low |
-| hc2/hc2_bm floor `1 - h_ii` at 1e-10 in the shared leverage meat, fabricating finite (if inflated) variances for leverage-one observations - hc3 now fails closed there (LWDiD fix wave) but the pre-existing hc2 family behavior is released surface; decide fail-closed vs keep-floor for hc2/hc2_bm | `diff_diff/linalg.py` | #588 | Quick | Low |
 | Numeric between-period cohorts (e.g. `first_treat=4.5` with integer times) are rejected by LWDiD while CallawaySantAnna estimates them and LWDiD's own datetime/Period cohorts map to the next observed period — close the dtype asymmetry by adopting the next-observed-period mapping for numeric cohorts too (contract documented in REGISTRY cohort-encodings Note + `docs/api/lwdid.rst` Input Contract). Lands only after PR #588 merges | `diff_diff/lwdid.py` | #588 | Quick | Low |
 | Implement the LW 2026 eq. 7.9/7.10 unit-average cohort estimand (regress per-unit post-average transformed outcomes on `[1, D_g]` vs never-treated) as an alternative to the documented cell-mass `cohort_effects` convention (REGISTRY within-cohort aggregation Note; the two differ on unbalanced panels, where cell-mass weights units by observed post periods). Needs the 7.10 regression + its covariance on the NT path. Lands only after PR #588 merges | `diff_diff/lwdid_staggered.py` | #588 | Quick | Low |
 | Expose cell-mass overall ATT (Stata `Post_avg` convention; = CS-simple on balanced panels) as an aggregate extra on LWDiD results — the fit's `.att` is the paper's `tau_omega` (cohort-mean-then-treated-weight, eq. 7.18); the authors' large-N display uses cell-mass weighting instead, and both are legitimate estimands (see the REGISTRY LWDiD Aggregation note). Lands only after PR #588 merges | `diff_diff/lwdid_results.py` | #588 | Quick | Low |

changelog.d/20260905-hc2-leverage-one.md

@@ -0,0 +1,20 @@
+### Behavioral Changes
+- **HC2 and unweighted, unclustered HC2-BM now fail closed at leverage one:**
+  an effective observation with hat-matrix leverage at least `1 - 1e-8`
+  produces a warning and entirely NaN covariance (and requested degrees of
+  freedom), preserving point estimates while suppressing undefined inference.
+  Python and Rust agree; over-one leverage no longer substitutes HC1.
+  Older Rust extensions without the fail-closed HC2 capability use NumPy
+  for HC2 while retaining their other accelerations.
+  Weighted and clustered HC2-BM retain their separate CR2 conventions,
+  including all-ones probability weights.
+
+### Fixed
+- **Zero-weight observations do not invalidate HC2/HC3 inference:** excluded
+  rows contribute zero to the covariance and cannot trigger the leverage
+  guard. Zero-frequency rows now agree with dropping those rows or expanding
+  the frequency counts literally.
+- **LWDiD uses the shared HC2 covariance guard:** leverage-one regressions
+  retain their point estimate and unavailable influence contribution while
+  emitting one covariance warning per regression, without a duplicate local
+  warning.

diff_diff/_backend.py

@@ -114,13 +114,13 @@
 except ImportError:
     _rust_batched_ridge_chol_solve = None
 
-# HC2 (leverage-corrected) robust vcov: imported independently for the same
-# mixed-version reason as demean_map (a stale extension missing only this
-# newer symbol degrades HC2 to the NumPy path without disabling the older
-# Rust accelerations).
+# HC2 requires the v2 fail-closed leverage contract. An older extension can
+# export the original symbol yet return finite covariance at unit leverage,
+# so symbol presence alone is insufficient. Import v2 independently: legacy
+# extensions use NumPy HC2 while retaining every other Rust acceleration.
 try:
     from diff_diff._rust_backend import (
-        compute_robust_vcov_hc2 as _rust_compute_robust_vcov_hc2,
+        compute_robust_vcov_hc2_v2 as _rust_compute_robust_vcov_hc2,
     )
 except ImportError:
     _rust_compute_robust_vcov_hc2 = None

diff_diff/estimators.py

@@ -109,13 +109,17 @@ class DifferenceInDifferences(BaseEstimator):
           (library default). With ``cluster=``, uses CR1 (Liang-Zeger).
         - ``"hc2"``: leverage-corrected meat (one-way only). Errors with
           ``cluster=``; use ``"hc2_bm"`` for clustered Bell-McCaffrey.
+          Effective leverage ``h_ii >= 1 - 1e-8`` produces a warning and
+          entirely NaN covariance/inference, retaining point estimates.
         - ``"hc2_bm"``: one-way HC2 + Imbens-Kolesar (2016) Satterthwaite DOF;
           with ``cluster=``, Pustejovsky-Tipton (2018) CR2 cluster-robust.
           ``MultiPeriodDiD(cluster=..., vcov_type="hc2_bm")`` is supported and
           uses a cluster-aware Bell-McCaffrey contrast DOF for the
           post-period-average ATT (see ``_compute_cr2_bm_contrast_dof`` in
           ``linalg.py`` and the REGISTRY.md note). Weighted CR2-BM
           (``survey_design=`` paths) is a separate gate.
+          Unweighted, unclustered fits share HC2's leverage-one NaN guard;
+          clustered CR2 and design-based survey inference are separate.
         - ``"hc3"``: jackknife-style leverage correction, meat
           ``e_i^2 / (1 - h_ii)^2`` (one-way only; errors with ``cluster=``).
           A leverage-one observation has no defined HC3 variance and the
@@ -2513,12 +2517,16 @@ class MultiPeriodDiD(DifferenceInDifferences):
           (library default). With ``cluster=``, uses CR1 (Liang-Zeger).
         - ``"hc2"``: leverage-corrected meat (one-way only). Errors with
           ``cluster=``; use ``"hc2_bm"`` without cluster for Bell-McCaffrey.
+          Effective leverage ``h_ii >= 1 - 1e-8`` produces a warning and
+          entirely NaN covariance/inference, retaining point estimates.
         - ``"hc2_bm"``: one-way HC2 + Imbens-Kolesar (2016) Satterthwaite DOF
           per coefficient plus a contrast-aware DOF for the post-period-average
           ATT. With ``cluster=``, dispatches to Pustejovsky-Tipton (2018)
           CR2 cluster-robust with a Bell-McCaffrey Satterthwaite contrast DOF
           on the post-period average (see ``cluster`` above for parity
           details). Weighted CR2-BM (``survey_design=``) is still gated.
+          Unweighted, unclustered fits share HC2's leverage-one NaN guard
+          for covariance and all contrast DOFs, including the average ATT.
         - ``"hc3"``: jackknife-style leverage correction, meat
           ``e_i^2 / (1 - h_ii)^2`` (one-way only; errors with ``cluster=``).
           A leverage-one observation has no defined HC3 variance and the