diff-diff 2.3.1__tar.gz → 2.3.2__tar.gz

{diff_diff-2.3.1 → diff_diff-2.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: diff-diff
-Version: 2.3.1
+Version: 2.3.2
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Science/Research
 Classifier: Operating System :: OS Independent
@@ -9,6 +9,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering :: Mathematics
 Requires-Dist: numpy>=1.20.0
 Requires-Dist: pandas>=1.3.0
@@ -28,7 +29,7 @@ Summary: A library for Difference-in-Differences causal inference analysis
 Keywords: causal-inference,difference-in-differences,econometrics,statistics,treatment-effects
 Author: diff-diff contributors
 License-Expression: MIT
-Requires-Python: >=3.9
+Requires-Python: >=3.9, <3.14
 Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
 Project-URL: Documentation, https://diff-diff.readthedocs.io
 Project-URL: Homepage, https://github.com/igerber/diff-diff
@@ -2489,7 +2490,7 @@ Returns DataFrame with columns: `unit`, `quality_score`, `outcome_trend_score`,
 
 ## Requirements
 
-- Python >= 3.9
+- Python 3.9 - 3.13
 - numpy >= 1.20
 - pandas >= 1.3
 - scipy >= 1.7

{diff_diff-2.3.1 → diff_diff-2.3.2}/README.md

@@ -2452,7 +2452,7 @@ Returns DataFrame with columns: `unit`, `quality_score`, `outcome_trend_score`,
 
 ## Requirements
 
-- Python >= 3.9
+- Python 3.9 - 3.13
 - numpy >= 1.20
 - pandas >= 1.3
 - scipy >= 1.7

{diff_diff-2.3.1 → diff_diff-2.3.2}/diff_diff/__init__.py

@@ -142,7 +142,7 @@ from diff_diff.datasets import (
     load_mpdta,
 )
 
-__version__ = "2.3.1"
+__version__ = "2.3.2"
 __all__ = [
     # Estimators
     "DifferenceInDifferences",

{diff_diff-2.3.1 → diff_diff-2.3.2}/diff_diff/staggered.py

@@ -415,6 +415,7 @@ class CallawaySantAnna(
             cohort_masks[g] = (unit_cohorts == g)
 
         # Never-treated mask
+        # np.inf was normalized to 0 in fit(), so the np.inf check is defensive only
         never_treated_mask = (unit_cohorts == 0) | (unit_cohorts == np.inf)
 
         # Pre-compute covariate matrices by time period if needed
@@ -639,13 +640,15 @@ class CallawaySantAnna(
         # This avoids hardcoding column names in internal methods
         df['first_treat'] = df[first_treat]
 
+        # Never-treated indicator (must precede treatment_groups to exclude np.inf)
+        df['_never_treated'] = (df[first_treat] == 0) | (df[first_treat] == np.inf)
+        # Normalize np.inf → 0 so all downstream `> 0` checks exclude never-treated
+        df.loc[df[first_treat] == np.inf, first_treat] = 0
+
         # Identify groups and time periods
         time_periods = sorted(df[time].unique())
         treatment_groups = sorted([g for g in df[first_treat].unique() if g > 0])
 
-        # Never-treated indicator (first_treat = 0 or inf)
-        df['_never_treated'] = (df[first_treat] == 0) | (df[first_treat] == np.inf)
-
         # Get unique units
         unit_info = df.groupby(unit).agg({
             first_treat: 'first',

{diff_diff-2.3.1 → diff_diff-2.3.2}/diff_diff/sun_abraham.py

@@ -456,9 +456,9 @@ class SunAbraham:
         covariates : list, optional
             List of covariate column names to include in regression.
         min_pre_periods : int, default=1
-            Minimum number of pre-treatment periods to include in event study.
+            **Deprecated**: Accepted but ignored. Will be removed in a future version.
         min_post_periods : int, default=1
-            Minimum number of post-treatment periods to include in event study.
+            **Deprecated**: Accepted but ignored. Will be removed in a future version.
 
         Returns
         -------
@@ -470,6 +470,22 @@ class SunAbraham:
         ValueError
             If required columns are missing or data validation fails.
         """
+        # Deprecation warnings for unimplemented parameters
+        if min_pre_periods != 1:
+            warnings.warn(
+                "min_pre_periods is not yet implemented and will be ignored. "
+                "This parameter will be removed in a future version.",
+                FutureWarning,
+                stacklevel=2,
+            )
+        if min_post_periods != 1:
+            warnings.warn(
+                "min_post_periods is not yet implemented and will be ignored. "
+                "This parameter will be removed in a future version.",
+                FutureWarning,
+                stacklevel=2,
+            )
+
         # Validate inputs
         required_cols = [outcome, unit, time, first_treat]
         if covariates:
@@ -486,13 +502,15 @@ class SunAbraham:
         df[time] = pd.to_numeric(df[time])
         df[first_treat] = pd.to_numeric(df[first_treat])
 
+        # Never-treated indicator (must precede treatment_groups to exclude np.inf)
+        df["_never_treated"] = (df[first_treat] == 0) | (df[first_treat] == np.inf)
+        # Normalize np.inf → 0 so all downstream `> 0` checks exclude never-treated
+        df.loc[df[first_treat] == np.inf, first_treat] = 0
+
         # Identify groups and time periods
         time_periods = sorted(df[time].unique())
         treatment_groups = sorted([g for g in df[first_treat].unique() if g > 0])
 
-        # Never-treated indicator
-        df["_never_treated"] = (df[first_treat] == 0) | (df[first_treat] == np.inf)
-
         # Get unique units
         unit_info = (
             df.groupby(unit)
@@ -533,9 +551,9 @@ class SunAbraham:
 
         all_rel_times_sorted = sorted(all_rel_times)
 
-        # Filter to reasonable range
-        min_rel = max(min(all_rel_times_sorted), -20)  # cap at -20
-        max_rel = min(max(all_rel_times_sorted), 20)   # cap at +20
+        # Use full range of relative times (no artificial truncation, matches R's fixest::sunab())
+        min_rel = min(all_rel_times_sorted)
+        max_rel = max(all_rel_times_sorted)
 
         # Reference period: last pre-treatment period (typically -1)
         self._reference_period = -1 - self.anticipation
@@ -765,12 +783,18 @@ class SunAbraham:
 
         # Fit OLS using LinearRegression helper (more stable than manual X'X inverse)
         cluster_ids = df_demeaned[cluster_var].values
+
+        # Degrees of freedom adjustment for absorbed unit and time fixed effects
+        n_units_fe = df[unit].nunique()
+        n_times_fe = df[time].nunique()
+        df_adj = n_units_fe + n_times_fe - 1
+
         reg = LinearRegression(
             include_intercept=False,  # Already demeaned, no intercept needed
             robust=True,
             cluster_ids=cluster_ids,
             rank_deficient_action=self.rank_deficient_action,
-        ).fit(X, y)
+        ).fit(X, y, df_adjustment=df_adj)
 
         coefficients = reg.coefficients_
         vcov = reg.vcov_
@@ -821,7 +845,8 @@ class SunAbraham:
 
         β_e = Σ_g w_{g,e} × δ_{g,e}
 
-        where w_{g,e} is the share of cohort g among treated units at relative time e.
+        where w_{g,e} = n_{g,e} / Σ_g n_{g,e} is the share of observations from cohort g
+        at event-time e among all treated observations at that event-time.
 
         Returns
         -------
@@ -833,9 +858,8 @@ class SunAbraham:
         event_study_effects: Dict[int, Dict[str, Any]] = {}
         cohort_weights: Dict[int, Dict[Any, float]] = {}
 
-        # Get cohort sizes
-        unit_cohorts = df.groupby(unit)[first_treat].first()
-        cohort_sizes = unit_cohorts[unit_cohorts > 0].value_counts().to_dict()
+        # Pre-compute per-event-time observation counts: n_{g,e}
+        event_time_counts = df[df[first_treat] > 0].groupby([first_treat, "_rel_time"]).size()
 
         for e in rel_periods:
             # Get cohorts that have observations at this relative time
@@ -847,13 +871,13 @@ class SunAbraham:
             if not cohorts_at_e:
                 continue
 
-            # Compute IW weights: share of each cohort among those observed at e
+            # Compute IW weights: n_{g,e} / Σ_g n_{g,e}
             weights = {}
             total_size = 0
             for g in cohorts_at_e:
-                n_g = cohort_sizes.get(g, 0)
-                weights[g] = n_g
-                total_size += n_g
+                n_g_e = event_time_counts.get((g, e), 0)
+                weights[g] = n_g_e
+                total_size += n_g_e
 
             if total_size == 0:
                 continue
@@ -915,7 +939,7 @@ class SunAbraham:
         ]
 
         if not post_effects:
-            return 0.0, 0.0
+            return np.nan, np.nan
 
         # Weight by number of treated observations at each relative time
         post_weights = []
@@ -948,7 +972,13 @@ class SunAbraham:
                         overall_weights_by_coef[key] += period_weight * cw
 
         if not overall_weights_by_coef:
-            # Fallback to simple variance calculation
+            # Fallback to simplified variance that ignores covariances between periods
+            warnings.warn(
+                "Could not construct full weight vector for overall ATT SE. "
+                "Using simplified variance that ignores covariances between periods.",
+                UserWarning,
+                stacklevel=2,
+            )
             overall_var = float(
                 np.sum((post_weights ** 2) * np.array([eff["se"] ** 2 for _, eff in post_effects]))
             )
@@ -1029,6 +1059,7 @@ class SunAbraham:
                 df_b[time] - df_b[first_treat],
                 np.nan
             )
+            # np.inf was normalized to 0 in fit(), so the np.inf check is defensive only
             df_b["_never_treated"] = (
                 (df_b[first_treat] == 0) | (df_b[first_treat] == np.inf)
             )
@@ -1113,11 +1144,16 @@ class SunAbraham:
             event_study_p_values[e] = p_value
 
         # Overall ATT statistics
-        overall_se = float(np.std(bootstrap_overall, ddof=1))
-        overall_ci = self._compute_percentile_ci(bootstrap_overall, self.alpha)
-        overall_p = self._compute_bootstrap_pvalue(
-            original_overall_att, bootstrap_overall
-        )
+        if not np.isfinite(original_overall_att):
+            overall_se = np.nan
+            overall_ci = (np.nan, np.nan)
+            overall_p = np.nan
+        else:
+            overall_se = float(np.std(bootstrap_overall, ddof=1))
+            overall_ci = self._compute_percentile_ci(bootstrap_overall, self.alpha)
+            overall_p = self._compute_bootstrap_pvalue(
+                original_overall_att, bootstrap_overall
+            )
 
         return SABootstrapResults(
             n_bootstrap=self.n_bootstrap,

{diff_diff-2.3.1 → diff_diff-2.3.2}/pyproject.toml

@@ -4,11 +4,11 @@ build-backend = "maturin"
 
 [project]
 name = "diff-diff"
-version = "2.3.1"
+version = "2.3.2"
 description = "A library for Difference-in-Differences causal inference analysis"
 readme = "README.md"
 license = "MIT"
-requires-python = ">=3.9"
+requires-python = ">=3.9,<3.14"
 authors = [
     {name = "diff-diff contributors"}
 ]
@@ -28,6 +28,7 @@ classifiers = [
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Topic :: Scientific/Engineering :: Mathematics",
 ]
 dependencies = [

{diff_diff-2.3.1 → diff_diff-2.3.2}/rust/Cargo.lock

@@ -173,7 +173,7 @@ checksum = "930c7171c8df9fb1782bdf9b918ed9ed2d33d1d22300abb754f9085bc48bf8e8"
 
 [[package]]
 name = "diff_diff_rust"
-version = "2.3.1"
+version = "2.3.2"
 dependencies = [
  "faer",
  "ndarray",
@@ -1376,9 +1376,9 @@ checksum = "2896d95c02a80c6d6a5d6e953d479f5ddf2dfdb6a244441010e373ac0fb88971"
 
 [[package]]
 name = "unicode-ident"
-version = "1.0.23"
+version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "537dd038a89878be9b64dd4bd1b260315c1bb94f4d784956b81e27a088d9a09e"
+checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
 
 [[package]]
 name = "unindent"

{diff_diff-2.3.1 → diff_diff-2.3.2}/rust/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "diff_diff_rust"
-version = "2.3.1"
+version = "2.3.2"
 edition = "2021"
 description = "Rust backend for diff-diff DiD library"
 license = "MIT"