docs: fix 86 Sphinx ERRORs across docstring substitutions and indentation

PR 1 of a 2-PR Sphinx cleanup sequence. Drops baseline ERROR count from
86 to 0 in `make html` output, unblocking eventual `-W` enforcement in
docs-tests.yml. WARNING count drops collaterally from 2,199 to 2,170
(systemic duplicate-object-description class deferred to PR 2).

Class A - Undefined substitution references (~50 instances).
RST treats `|X|` as a substitution-reference; on `|ATT|`, `|overall ATT|`,
`|DID_M|`, `|h|`, `|Omega_0|`, `|delta_{...}|`, etc. with no defined
substitution, the build errors. Per-context fix:
- coef_var docstrings across results.py, *_results.py: `SE / |ATT|`
  -> `SE / abs(ATT)` (plain English, readable in `help()`).
- imputation.py / two_stage.py horizon parameter: `|h|` -> `abs(h)`.
- imputation_results.py matrix-cardinality: `|Omega_1|` ->
  `:math:\`|\Omega_1|\``.
- honest_did.py Delta-class smoothness/relative-magnitude restrictions:
  inline `|delta_{t+1} - delta_t|` math -> `.. math::` block (DeltaSD,
  DeltaRM) or inline `:math:` (DeltaSDRM list items), with `\delta`
  LaTeX rendering.
- trop.py / trop_results.py / docs/api/trop.rst: `|s-t|` and `|t-s|` ->
  `:math:\`|s-t|\``.

Class B - Unexpected indentation in numpydoc bullet lists.
RST requires a blank line between a colon-terminated description line
and the bullet list that follows. Affected sites use the same pattern:
parameter `X : type` description ending with `:`, then bullets without
blank line. Fix is a single inserted blank line per site, applied to:
- bacon.py:bacon_decompose (weights param + Returns block)
- staggered.py:CallawaySantAnna (rank_deficient_action, base_period,
  pscore_fallback)
- triple_diff.py:TripleDifference (estimation_method,
  rank_deficient_action, pscore_fallback)
- twfe.py:TwoWayFixedEffects.decompose (weights param)
- synthetic_did.py:SyntheticDiD (use-cases bullet list,
  variance_method)
- prep.py:rank_control_units (Returns columns)
- had.py:HeterogeneousAdoptionDiDResults (se attribute bullets)
- results.py:SyntheticDiDResults.get_loo_effects_df (Available on,
  Blocked on, Returns columns)

Other fixes:
- diagnostic_report.py:DiagnosticReport - collapsed multi-line
  parameter name list (`run_parallel_trends, run_sensitivity, ...`) to
  single line so RST recognizes the parameter group; replaced em-dash
  with hyphen per repo convention.
- docs/api/local_linear.rst:48 - replaced `.. autodata:: KERNELS`
  (which Sphinx tries to construct a docstring for via autodoc, hitting
  RST parse errors on the surrounding source comments) with manual
  `.. py:data::` directive carrying the same content.

Out of scope (queued):
- 2,170 systemic `duplicate object description` warnings from
  page-level autoclass `:members:` overlapping with autosummary stubs
  (PR 2: most likely add `:no-index:` to ~25-30 page-level directives
  per Sphinx's recommended fix).
- Adding `-W` to `docs-tests.yml` (PR 3, after PR 2).

Verification:
- `make html`: 0 ERRORs (was 86), 2,170 WARNINGs (was 2,199).
- `pytest tests/test_doc_snippets.py`: 111 passed, 4 skipped (unchanged
  baseline).
- 0 em-dashes in diff.

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

Author: igerber

diff_diff/bacon.py

@@ -1085,6 +1085,7 @@ def bacon_decompose(
         Use 0 (or np.inf) for never-treated units.
     weights : str, default="approximate"
         Weight calculation method:
+
         - "approximate": Fast simplified formula (default). Good for
           diagnostic purposes where relative weights are sufficient.
         - "exact": Variance-based weights from Goodman-Bacon (2021)
@@ -1094,6 +1095,7 @@ def bacon_decompose(
     -------
     BaconDecompositionResults
         Object containing decomposition results with:
+
         - twfe_estimate: The overall TWFE coefficient
         - comparisons: List of all 2x2 comparisons with estimates and weights
         - Weight totals by comparison type

diff_diff/chaisemartin_dhaultfoeuille_results.py

@@ -701,7 +701,7 @@ def __repr__(self) -> str:
 
     @property
     def coef_var(self) -> float:
-        """SE / |DID_M|; NaN when DID_M is 0 or SE non-finite."""
+        """SE / abs(DID_M); NaN when DID_M is 0 or SE non-finite."""
         if not (np.isfinite(self.overall_se) and self.overall_se >= 0):
             return np.nan
         if not np.isfinite(self.overall_att) or self.overall_att == 0:

diff_diff/continuous_did_results.py

@@ -156,7 +156,7 @@ def __repr__(self) -> str:
 
     @property
     def coef_var(self) -> float:
-        """Coefficient of variation: SE / |overall ATT|. NaN when ATT is 0 or SE non-finite."""
+        """Coefficient of variation: SE / abs(overall ATT). NaN when ATT is 0 or SE non-finite."""
         if not (np.isfinite(self.overall_att_se) and self.overall_att_se >= 0):
             return np.nan
         if not np.isfinite(self.overall_att) or self.overall_att == 0:

diff_diff/diagnostic_report.py

@@ -256,10 +256,9 @@ class DiagnosticReport:
         Column names identifying the panel structure.
     pre_periods, post_periods : list, optional
         Explicit pre- and post-treatment period labels.
-    run_parallel_trends, run_sensitivity, run_placebo, run_bacon,
-    run_design_effect, run_heterogeneity, run_epv, run_pretrends_power : bool
+    run_parallel_trends, run_sensitivity, run_placebo, run_bacon, run_design_effect, run_heterogeneity, run_epv, run_pretrends_power : bool
         Per-check opt-in flags. ``run_placebo`` defaults to ``False`` (opt-in,
-        expensive, currently not implemented — placebo key remains reserved
+        expensive, currently not implemented - placebo key remains reserved
         as ``skipped`` in the schema). All other checks default to ``True``
         and are further gated by estimator-type and instance-level
         applicability (see ``docs/methodology/REPORTING.md``).

diff_diff/efficient_did_results.py

@@ -180,7 +180,7 @@ def __repr__(self) -> str:
 
     @property
     def coef_var(self) -> float:
-        """Coefficient of variation: SE / |overall ATT|. NaN when ATT is 0 or SE non-finite."""
+        """Coefficient of variation: SE / abs(overall ATT). NaN when ATT is 0 or SE non-finite."""
         if not (np.isfinite(self.overall_se) and self.overall_se >= 0):
             return np.nan
         if not np.isfinite(self.overall_att) or self.overall_att == 0:

diff_diff/had.py

@@ -233,6 +233,7 @@ class HeterogeneousAdoptionDiDResults:
           ``(Ybar_{Z=1} - Ybar_{Z=0}) / (Dbar_{Z=1} - Dbar_{Z=0})``.
     se : float
         Standard error on the beta-scale. For continuous designs:
+
         - Unweighted or ``weights=<array>``: CCT-2014 weighted-robust SE
           from Phase 1c divided by ``|den|`` (``den`` = raw or weighted
           denominator depending on fit path).
@@ -241,6 +242,7 @@ class HeterogeneousAdoptionDiDResults:
           aligned with ``tau_bc``) routed through
           :func:`compute_survey_if_variance` for PSU-aggregated,
           FPC/strata-adjusted variance, divided by ``|den|``.
+
         In both cases the higher-order variance from ``mean(ΔY)`` is
         dominated by the nonparametric boundary estimate in large
         samples and is not included in the leading-order formula. For

diff_diff/honest_did.py

@@ -40,7 +40,10 @@ class DeltaSD:
     Smoothness restriction on trend violations (Delta^{SD}).
 
     Restricts the second differences of the trend violations:
-        |delta_{t+1} - 2*delta_t + delta_{t-1}| <= M
+
+    .. math::
+
+        |\\delta_{t+1} - 2\\delta_t + \\delta_{t-1}| \\le M
 
     When M=0, this enforces that violations follow a linear trend
     (linear extrapolation of pre-trends). Larger M allows more
@@ -75,7 +78,10 @@ class DeltaRM:
 
     Post-treatment consecutive first differences are bounded by Mbar
     times the maximum pre-treatment first difference:
-        |delta_{t+1} - delta_t| <= Mbar * max_{s<0} |delta_{s+1} - delta_s|
+
+    .. math::
+
+        |\\delta_{t+1} - \\delta_t| \\le \\overline{M} \\cdot \\max_{s<0} |\\delta_{s+1} - \\delta_s|
 
     When Mbar=0, this enforces zero post-treatment first differences.
     Mbar=1 means post-period first differences can be as large as the
@@ -109,8 +115,9 @@ class DeltaSDRM:
     Combined smoothness and relative magnitudes restriction.
 
     Imposes both:
-    1. Smoothness: |delta_{t+1} - 2*delta_t + delta_{t-1}| <= M
-    2. Relative magnitudes: |delta_{t+1} - delta_t| <= Mbar * max_{s<0} |delta_{s+1} - delta_s|
+
+    1. Smoothness: :math:`|\\delta_{t+1} - 2\\delta_t + \\delta_{t-1}| \\le M`
+    2. Relative magnitudes: :math:`|\\delta_{t+1} - \\delta_t| \\le \\overline{M} \\cdot \\max_{s<0} |\\delta_{s+1} - \\delta_s|`
 
     This is more restrictive than either constraint alone.
 

diff_diff/imputation.py

@@ -75,7 +75,7 @@ class ImputationDiD(ImputationDiDBootstrapMixin):
         - "silent": Drop columns silently
     horizon_max : int, optional
         Maximum event-study horizon. If set, event study effects are only
-        computed for |h| <= horizon_max.
+        computed for abs(h) <= horizon_max.
     aux_partition : str, default="cohort_horizon"
         Controls the auxiliary model partition for Theorem 3 variance:
         - "cohort_horizon": Groups by cohort x relative time (tightest SEs)

diff_diff/imputation_results.py

@@ -104,9 +104,9 @@ class ImputationDiDResults:
     n_obs : int
         Total number of observations.
     n_treated_obs : int
-        Number of treated observations (|Omega_1|).
+        Number of treated observations (:math:`|\\Omega_1|`).
     n_untreated_obs : int
-        Number of untreated observations (|Omega_0|).
+        Number of untreated observations (:math:`|\\Omega_0|`).
     n_treated_units : int
         Number of ever-treated units.
     n_control_units : int
@@ -155,7 +155,7 @@ def __repr__(self) -> str:
 
     @property
     def coef_var(self) -> float:
-        """Coefficient of variation: SE / |overall ATT|. NaN when ATT is 0 or SE non-finite."""
+        """Coefficient of variation: SE / abs(overall ATT). NaN when ATT is 0 or SE non-finite."""
         if not (np.isfinite(self.overall_se) and self.overall_se >= 0):
             return np.nan
         if not np.isfinite(self.overall_att) or self.overall_att == 0:

diff_diff/prep.py

@@ -834,6 +834,7 @@ def rank_control_units(
     -------
     pd.DataFrame
         Ranked control units with columns:
+
         - unit: Unit identifier
         - quality_score: Combined quality score (0-1, higher is better)
         - outcome_trend_score: Pre-treatment outcome trend similarity
@@ -846,6 +847,7 @@ def rank_control_units(
         - is_required: Whether unit was in require_units
 
         If suggest_treatment_candidates=True (and no treated units):
+
         - unit: Unit identifier
         - treatment_candidate_score: Suitability as treatment unit
         - avg_outcome_level: Pre-treatment outcome mean