R2 local Codex polish: pin the SAME compound contrast as the R fixture

Local Codex R2 returned ✅ with 1 substantive P3: the new MPD parity
test was fitting MPD without an explicit `post_periods=` argument, so
MPD's default "last half of periods" rule selected `[3, 4]` on the
4-period fixture while the R generator defines the parity contrast
over `[2, 3, 4]` (per `post_interaction_names` in the JSON). The
Satterthwaite DOFs happened to coincide here (~8.1) which masked the
estimand mismatch — the test would have stayed green if MPD silently
fit the wrong contrast.

Fix: derive `post_periods` from the golden JSON's
`post_interaction_names` field and pass it explicitly to MPD.fit().
The test now asserts that MPD computes `avg_att` over the exact same
contrast vector R uses for the Wald_test DOF target.

This makes the test a genuine estimand-level parity pin rather than
just a DOF-magnitude smell check.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: igerber

tests/test_estimators_vcov_type.py

@@ -582,13 +582,23 @@ def test_multi_period_cluster_hc2_bm_avg_att_uses_clubsandwich_dof(self):
         )
         # MPD parameterization with `fixed_effects=["unit"]` matches the R
         # generator's `factor(unit)` term (the cluster column is the unit).
+        # Derive `post_periods` from the R `post_interaction_names` so the
+        # contrast we compare to is the SAME `c_avg = (1/n_post) Σ e_p` that
+        # the R generator builds. Without this, MPD defaults to the
+        # last-half-of-periods rule and computes avg_att over [3, 4] on this
+        # 4-period panel, but the R fixture's `c_avg` is over [2, 3, 4] —
+        # the DOFs happen to coincide here but the avg_att estimands differ.
+        post_periods = [
+            int(name.rsplit("_", 1)[1]) for name in d["post_interaction_names"]
+        ]
         res = MultiPeriodDiD(vcov_type="hc2_bm", cluster="unit").fit(
             data,
             outcome="y",
             treatment="treated",
             time="period",
             fixed_effects=["unit"],
             reference_period=int(d["reference_period"]),
+            post_periods=post_periods,
             unit="unit",
         )
         assert np.isfinite(res.avg_att) and np.isfinite(res.avg_se)