Add webb bootstrap weight tests, document TROP n_bootstrap constraint for PR #165 round 4

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: igerber

docs/methodology/REGISTRY.md

@@ -941,6 +941,7 @@ Q(λ) = Σ_{j,s: D_js=0} [τ̂_js^loocv(λ)]²
   - **n_post_periods metadata**: Counts periods where D=1 is actually observed (at least one unit has D=1), not calendar periods from first treatment. In unbalanced panels where treated units are missing in some post-treatment periods, only periods with observed D=1 values are counted.
 - Wrong D specification: if user provides event-style D (only first treatment period),
   the absorbing-state validation will raise ValueError with helpful guidance
+- **Bootstrap minimum**: `n_bootstrap` must be >= 2 (enforced via `ValueError`). TROP uses bootstrap for all variance estimation — there is no analytical SE formula.
 - **LOOCV failure metadata**: When LOOCV fits fail in the Rust backend, the first failed observation coordinates (t, i) are returned to Python for informative warning messages
 - **Inference CI distribution**: After `safe_inference()` migration, CI uses t-distribution (df = max(1, n_treated_obs - 1)), consistent with p_value. Previously CI used normal-distribution while p_value used t-distribution (inconsistent). This is a minor behavioral change; CIs may be slightly wider for small n_treated_obs.
 

tests/test_imputation.py

@@ -1104,6 +1104,21 @@ def test_bootstrap_weights_mammen(self, ci_params):
         assert br.overall_att_se > 0
         assert np.isfinite(br.overall_att_p_value)
 
+    def test_bootstrap_weights_webb(self, ci_params):
+        """Bootstrap with webb weights should produce valid results."""
+        data = generate_test_data()
+        n_boot = ci_params.bootstrap(50)
+        est = ImputationDiD(n_bootstrap=n_boot, bootstrap_weights="webb", seed=42)
+        results = est.fit(
+            data, outcome="outcome", unit="unit", time="time", first_treat="first_treat",
+        )
+
+        br = results.bootstrap_results
+        assert br is not None
+        assert br.weight_type == "webb"
+        assert br.overall_att_se > 0
+        assert np.isfinite(br.overall_att_p_value)
+
     def test_bootstrap_with_covariates(self, ci_params):
         """Bootstrap should work with covariates."""
         data = generate_test_data()

tests/test_two_stage.py

@@ -1076,6 +1076,22 @@ def test_bootstrap_weights_mammen(self, ci_params):
         assert br.overall_att_se > 0
         assert np.isfinite(br.overall_att_p_value)
 
+    def test_bootstrap_weights_webb(self, ci_params):
+        """Bootstrap with webb weights should produce valid results."""
+        data = generate_test_data()
+        n_boot = ci_params.bootstrap(50)
+        results = TwoStageDiD(
+            n_bootstrap=n_boot, bootstrap_weights="webb", seed=42
+        ).fit(
+            data, outcome="outcome", unit="unit", time="time", first_treat="first_treat"
+        )
+
+        br = results.bootstrap_results
+        assert br is not None
+        assert br.weight_type == "webb"
+        assert br.overall_att_se > 0
+        assert np.isfinite(br.overall_att_p_value)
+
 
 # =============================================================================
 # TestTwoStageDiDConvenience