docs: fix 86 Sphinx ERRORs (PR 1 of 2-PR cleanup)

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

diff_diff/results.py

@@ -141,7 +141,7 @@ def __repr__(self) -> str:
 
     @property
     def coef_var(self) -> float:
-        """Coefficient of variation: SE / |ATT|. NaN when ATT is 0 or SE non-finite."""
+        """Coefficient of variation: SE / abs(ATT). NaN when ATT is 0 or SE non-finite."""
         if not (np.isfinite(self.se) and self.se >= 0):
             return np.nan
         if not np.isfinite(self.att) or self.att == 0:
@@ -468,7 +468,7 @@ def post_period_effects(self) -> Dict[Any, PeriodEffect]:
 
     @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.avg_se) and self.avg_se >= 0):
             return np.nan
         if not np.isfinite(self.avg_att) or self.avg_att == 0:
@@ -919,7 +919,7 @@ def __getstate__(self) -> Dict[str, Any]:
 
     @property
     def coef_var(self) -> float:
-        """Coefficient of variation: SE / |ATT|. NaN when ATT is 0 or SE non-finite."""
+        """Coefficient of variation: SE / abs(ATT). NaN when ATT is 0 or SE non-finite."""
         if not (np.isfinite(self.se) and self.se >= 0):
             return np.nan
         if not np.isfinite(self.att) or self.att == 0:
@@ -1114,14 +1114,16 @@ def get_loo_effects_df(self) -> pd.DataFrame:
         full-design survey jackknife path, which uses PSU-level LOO).
 
         Available on:
+
         * non-survey jackknife fits (classical Arkhangelsky Algorithm 3).
         * pweight-only survey jackknife fits (Algorithm 3 with post-hoc
           ω_eff composition; PSU labels in ``survey_metadata`` come from
           implicit-PSU metadata but the LOO remains unit-level).
 
         Blocked on:
+
         * full-design survey jackknife fits (strata / PSU / FPC set in
-          ``SurveyDesign``) — the underlying replicates are PSU-level
+          ``SurveyDesign``) - the underlying replicates are PSU-level
           ``τ̂_{(h,j)}`` (Rust & Rao 1996), not unit-level. See
           ``result.placebo_effects`` for the raw PSU-level replicate
           array and REGISTRY §SyntheticDiD "Note (survey + jackknife
@@ -1142,10 +1144,12 @@ def get_loo_effects_df(self) -> pd.DataFrame:
         -------
         pd.DataFrame
             Columns:
-                - ``unit`` — user's unit ID
-                - ``role`` — ``'control'`` or ``'treated'``
-                - ``att_loo`` — ATT with this unit dropped
-                - ``delta_from_full`` — ``att_loo - self.att``
+
+            - ``unit`` - user's unit ID
+            - ``role`` - ``'control'`` or ``'treated'``
+            - ``att_loo`` - ATT with this unit dropped
+            - ``delta_from_full`` - ``att_loo - self.att``
+
             Sorted by ``|delta_from_full|`` descending, NaN rows at the end.
         """
         if self.variance_method != "jackknife":

diff_diff/stacked_did_results.py

@@ -109,7 +109,7 @@ 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/staggered.py

@@ -175,16 +175,19 @@ class CallawaySantAnna(
         Random seed for reproducibility.
     rank_deficient_action : str, default="warn"
         Action when design matrix is rank-deficient (linearly dependent columns):
+
         - "warn": Issue warning and drop linearly dependent columns (default)
         - "error": Raise ValueError
         - "silent": Drop columns silently without warning
     base_period : str, default="varying"
         Method for selecting the base (reference) period for computing
         ATT(g,t). Options:
+
         - "varying": For pre-treatment periods (t < g - anticipation), use
           t-1 as base (consecutive comparisons). For post-treatment, use
           g-1-anticipation. Requires t-1 to exist in data.
         - "universal": Always use g-1-anticipation as base period.
+
         Both produce identical post-treatment effects. Matches R's
         did::att_gt() base_period parameter.
     cband : bool, default=True
@@ -217,12 +220,14 @@ class CallawaySantAnna(
     pscore_fallback : str, default="error"
         Action when propensity score estimation fails entirely
         (``LinAlgError`` or ``ValueError`` from IRLS):
+
         - "error": Raise the exception (default). Ensures the user is
           aware of estimation failures.
         - "unconditional": Fall back to unconditional propensity
           with a warning. For IPW, this drops all covariates. For DR,
           the propensity model becomes unconditional but outcome
           regression still uses covariates.
+
         When ``rank_deficient_action="error"``, errors are always
         re-raised regardless of this setting.
 

diff_diff/staggered_results.py

@@ -150,7 +150,7 @@ 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/staggered_triple_diff_results.py

@@ -107,7 +107,7 @@ 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/sun_abraham.py

@@ -105,7 +105,7 @@ 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/synthetic_did.py

@@ -35,6 +35,7 @@ class SyntheticDiD(DifferenceInDifferences):
     pre-treatment trends.
 
     This method is particularly useful when:
+
     - You have few treated units (possibly just one)
     - Parallel trends assumption may be questionable
     - Control units are heterogeneous and need reweighting
@@ -52,6 +53,7 @@ class SyntheticDiD(DifferenceInDifferences):
         Significance level for confidence intervals.
     variance_method : str, default="placebo"
         Method for variance estimation:
+
         - "placebo": Placebo-based variance matching R's synthdid::vcov(method="placebo").
           Implements Algorithm 4 from Arkhangelsky et al. (2021). Library default
           (R's default is ``"bootstrap"``; we default to placebo because it is

diff_diff/triple_diff.py

@@ -365,6 +365,7 @@ class TripleDifference:
     ----------
     estimation_method : str, default="dr"
         Estimation method to use:
+
         - "dr": Doubly robust (recommended). Consistent if either the outcome
           model or propensity score model is correctly specified.
         - "reg": Regression adjustment (outcome regression).
@@ -385,6 +386,7 @@ class TripleDifference:
         or above (1 - pscore_trim) are clipped to avoid extreme weights.
     rank_deficient_action : str, default="warn"
         Action when design matrix is rank-deficient (linearly dependent columns):
+
         - "warn": Issue warning and drop linearly dependent columns (default)
         - "error": Raise ValueError
         - "silent": Drop columns silently without warning
@@ -397,11 +399,13 @@ class TripleDifference:
         (1996). Only applies to IPW and DR estimation methods.
     pscore_fallback : str, default="error"
         Action when propensity score estimation fails:
+
         - "error": Raise the exception (default)
         - "unconditional": Fall back to unconditional propensity with
           a warning. For IPW, drops all covariates. For DR, the
           propensity model becomes unconditional but outcome regression
           still uses covariates.
+
         When ``rank_deficient_action="error"``, errors are always
         re-raised regardless of this setting.
 

diff_diff/trop.py

@@ -53,7 +53,7 @@ class TROP(TROPLocalMixin, TROPGlobalMixin):
     2. **Exponential distance-based unit weights**: ω_j = exp(-λ_unit × d(j,i))
        where d(j,i) is the RMSE of outcome differences between units
 
-    3. **Exponential time decay weights**: θ_s = exp(-λ_time × |s-t|)
+    3. **Exponential time decay weights**: θ_s = exp(-λ_time × :math:`|s-t|`)
        weighting pre-treatment periods by proximity to treatment
 
     Tuning parameters (λ_time, λ_unit, λ_nn) are selected via leave-one-out

diff_diff/trop_results.py

@@ -162,7 +162,7 @@ def __repr__(self) -> str:
 
     @property
     def coef_var(self) -> float:
-        """Coefficient of variation: SE / |ATT|. NaN when ATT is 0 or SE non-finite."""
+        """Coefficient of variation: SE / abs(ATT). NaN when ATT is 0 or SE non-finite."""
         if not (np.isfinite(self.se) and self.se >= 0):
             return np.nan
         if not np.isfinite(self.att) or self.att == 0:

diff_diff/twfe.py

@@ -602,6 +602,7 @@ def 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)

diff_diff/two_stage.py

@@ -86,7 +86,7 @@ class TwoStageDiD(TwoStageDiDBootstrapMixin):
         - "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.
     pretrends : bool, default=False
         If True, event study includes pre-treatment horizons for visual
         pre-trends assessment. Pre-period effects should be ~0 under

diff_diff/two_stage_results.py

@@ -153,7 +153,7 @@ 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:

docs/api/local_linear.rst

@@ -45,14 +45,10 @@ to ``int_0^1 k(u) du = 1/2``; the uniform kernel uses
 
 .. autofunction:: diff_diff.uniform_kernel
 
-.. autodata:: diff_diff.KERNELS
-   :annotation: : dict[str, Callable[[np.ndarray], np.ndarray]]
-   :no-value:
-
-   Mapping from kernel name (``"epanechnikov"`` / ``"triangular"`` /
-   ``"uniform"``) to its callable evaluator on ``[0, 1]``. Pass the name
-   string (not the callable) to ``local_linear_fit`` and
-   ``mse_optimal_bandwidth`` via their ``kernel=`` argument.
+.. py:data:: diff_diff.KERNELS
+   :type: dict[str, Callable[[np.ndarray], np.ndarray]]
+
+   Mapping from kernel name (``"epanechnikov"`` / ``"triangular"`` / ``"uniform"``) to its callable evaluator on ``[0, 1]``. Pass the name string (not the callable) to ``local_linear_fit`` and ``mse_optimal_bandwidth`` via their ``kernel=`` argument.
 
 .. autofunction:: diff_diff.kernel_moments