Extend dCDH PSU-level wild bootstrap to cell granularity

CHANGELOG.md

@@ -9,7 +9,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 - Add Zenodo DOI badge to README; upgrade the BibTeX citation block with the concept DOI (`10.5281/zenodo.19646175`) and list author as Isaac Gerber (matching `CITATION.cff`). Add `doi:` and `identifiers:` entries (concept + versioned) to `CITATION.cff`. DOI was minted by Zenodo when v3.1.3 was released.
-- **`ChaisemartinDHaultfoeuille` heterogeneity + within-group-varying PSU/strata now supported under Binder TSL** - `fit(heterogeneity=..., survey_design=...)` no longer raises `NotImplementedError` when the resolved design's PSU or strata vary across the cells of a group. On the **Binder TSL** branch (`compute_survey_if_variance`), the heterogeneity WLS coefficient IF is expanded to observation level via the cell-period allocator `ψ_i = ψ_g * (w_i / W_{g, out_idx})` on the post-period cell — the DID_l post-period single-cell convention shipped in v3.1.x. Under PSU=group the PSU-level Binder TSL variance is byte-identical to the previous release (PSU-level aggregate telescopes to `ψ_g`); under within-group-varying PSU, mass lands in the post-period PSU of the transition. The **Rao-Wu replicate-weight** branch (`compute_replicate_if_variance`) retains the legacy group-level allocator `ψ_i = ψ_g * (w_i / W_g)`: replicate variance computes `θ_r = sum_i ratio_ir * ψ_i` at observation level and is therefore not PSU-telescoping, so the cell-period allocator would silently change the replicate SE whenever a replicate column's ratios vary within group (e.g., per-row replicate matrices). Replicate + heterogeneity fits therefore produce byte-identical SE to the previous release, and the newly-unblocked `heterogeneity=` + within-group-varying PSU combination is unreachable under replicate designs by construction (`SurveyDesign` rejects `replicate_weights` combined with explicit `strata/psu/fpc`). `n_bootstrap > 0` combined with within-group-varying PSU remains gated with `NotImplementedError` — the PSU-level Hall-Mammen wild bootstrap still uses the legacy group-level PSU map and will be extended in a follow-up PR.
+- **`ChaisemartinDHaultfoeuille` heterogeneity + within-group-varying PSU/strata now supported under Binder TSL** - `fit(heterogeneity=..., survey_design=...)` no longer raises `NotImplementedError` when the resolved design's PSU or strata vary across the cells of a group. On the **Binder TSL** branch (`compute_survey_if_variance`), the heterogeneity WLS coefficient IF is expanded to observation level via the cell-period allocator `ψ_i = ψ_g * (w_i / W_{g, out_idx})` on the post-period cell — the DID_l post-period single-cell convention shipped in v3.1.x. Under PSU=group the PSU-level Binder TSL variance is byte-identical to the previous release (PSU-level aggregate telescopes to `ψ_g`); under within-group-varying PSU, mass lands in the post-period PSU of the transition. The **Rao-Wu replicate-weight** branch (`compute_replicate_if_variance`) retains the legacy group-level allocator `ψ_i = ψ_g * (w_i / W_g)`: replicate variance computes `θ_r = sum_i ratio_ir * ψ_i` at observation level and is therefore not PSU-telescoping, so the cell-period allocator would silently change the replicate SE whenever a replicate column's ratios vary within group (e.g., per-row replicate matrices). Replicate + heterogeneity fits therefore produce byte-identical SE to the previous release, and the newly-unblocked `heterogeneity=` + within-group-varying PSU combination is unreachable under replicate designs by construction (`SurveyDesign` rejects `replicate_weights` combined with explicit `strata/psu/fpc`).
+- **`ChaisemartinDHaultfoeuille.fit(survey_design=..., n_bootstrap > 0)` now supports within-group-varying PSU** — the PSU-level Hall-Mammen wild multiplier bootstrap has been extended from a group-level PSU map (one multiplier per group) to a cell-level PSU map (one multiplier per `(g, t)` cell's PSU). A dispatcher in `_compute_dcdh_bootstrap` detects PSU-within-group-constant regimes (including PSU=group auto-inject and strictly-coarser PSU with within-group constancy) and routes them through the legacy group-level path so the bootstrap SE is bit-identical to the previous release (guarded by the new `test_bootstrap_se_matches_pre_pr4_baseline` and the pre-existing `test_auto_inject_bit_identical_to_group_level`). Under within-group-varying PSU, a group contributing cells to multiple PSUs receives independent multiplier draws per PSU — the correct Hall-Mammen wild PSU clustering at cell granularity. Multi-horizon bootstraps draw a single shared `(n_bootstrap, n_psu)` PSU-level weight matrix per block and broadcast per-horizon via each horizon's cell-to-PSU map, so the sup-t simultaneous confidence band remains a valid joint distribution. Closes the last `NotImplementedError` gate in the dCDH survey contract; replicate-weight variance and `n_bootstrap > 0` remain mutually exclusive by construction. **Scope note:** panels with *terminal missingness* where the terminally-missing group is in a cohort whose other groups still contribute at the missing period now raise a targeted `ValueError` on every survey variance path that uses the cell-period allocator: Binder TSL with within-group-varying PSU, Rao-Wu replicate-weight ATT (which always uses the cell allocator per the Class A contract shipped in PR #323), and the cell-level wild PSU bootstrap. Cohort-recentering leaks centered IF mass onto cells with no positive-weight observations, which the cell-period allocator cannot attach to any observation/PSU. This closes a silent mass-drop bug the cell-period allocator introduced across all three paths in v3.1.x; pre-process the panel to remove terminal missingness (drop late-exit groups or trim to a balanced sub-panel) as the documented workaround. For Binder TSL only, using an explicit `psu=<group_col>` routes through the legacy group-level allocator where the row-sum identity makes the two allocators statistically equivalent. Replicate-weight ATT and within-group-varying-PSU bootstrap have no such allocator fallback — the panel itself must be pre-processed. PSU-within-group-constant Binder TSL (including PSU=group auto-inject) is unaffected.
 
 ## [3.1.3] - 2026-04-18