diff-diff 2.4.3__tar.gz → 2.6.0__tar.gz

{diff_diff-2.4.3 → diff_diff-2.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: diff-diff
-Version: 2.4.3
+Version: 2.6.0
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Science/Research
 Classifier: Operating System :: OS Independent
@@ -108,7 +108,7 @@ Signif. codes: '***' 0.001, '**' 0.01, '*' 0.05, '.' 0.1
 - **Wild cluster bootstrap**: Valid inference with few clusters (<50) using Rademacher, Webb, or Mammen weights
 - **Panel data support**: Two-way fixed effects estimator for panel designs
 - **Multi-period analysis**: Event-study style DiD with period-specific treatment effects
-- **Staggered adoption**: Callaway-Sant'Anna (2021), Sun-Abraham (2021), Borusyak-Jaravel-Spiess (2024) imputation, and Two-Stage DiD (Gardner 2022) estimators for heterogeneous treatment timing
+- **Staggered adoption**: Callaway-Sant'Anna (2021), Sun-Abraham (2021), Borusyak-Jaravel-Spiess (2024) imputation, Two-Stage DiD (Gardner 2022), and Stacked DiD (Wing, Freedman & Hollingsworth 2024) estimators for heterogeneous treatment timing
 - **Triple Difference (DDD)**: Ortiz-Villavicencio & Sant'Anna (2025) estimators with proper covariate handling
 - **Synthetic DiD**: Combined DiD with synthetic control for improved robustness
 - **Triply Robust Panel (TROP)**: Factor-adjusted DiD with synthetic weights (Athey et al. 2025)
@@ -138,6 +138,9 @@ We provide Jupyter notebook tutorials in `docs/tutorials/`:
 | `08_triple_diff.ipynb` | Triple Difference (DDD) estimation with proper covariate handling |
 | `09_real_world_examples.ipynb` | Real-world data examples (Card-Krueger, Castle Doctrine, Divorce Laws) |
 | `10_trop.ipynb` | Triply Robust Panel (TROP) estimation with factor model adjustment |
+| `11_imputation_did.ipynb` | Imputation DiD (Borusyak et al. 2024), pre-trend test, efficiency comparison |
+| `12_two_stage_did.ipynb` | Two-Stage DiD (Gardner 2022), GMM sandwich variance, per-observation effects |
+| `13_stacked_did.ipynb` | Stacked DiD (Wing et al. 2024), Q-weights, sub-experiment inspection, trimming, clean control definitions |
 
 ## Data Preparation
 
@@ -1012,6 +1015,78 @@ TwoStageDiD(
 
 Both estimators are the efficient estimator under homogeneous treatment effects, producing shorter confidence intervals than Callaway-Sant'Anna or Sun-Abraham.
 
+### Stacked DiD (Wing, Freedman & Hollingsworth 2024)
+
+Stacked DiD addresses TWFE bias in staggered adoption settings by constructing a "clean" comparison dataset for each treatment cohort and stacking them together. Each cohort's sub-experiment compares units treated at that cohort's timing against units that are not yet treated (or never treated) within a symmetric event-study window. This avoids the "bad comparisons" problem in TWFE while retaining a regression-based framework that practitioners familiar with event studies will find intuitive.
+
+```python
+from diff_diff import StackedDiD, generate_staggered_data
+
+# Generate sample data
+data = generate_staggered_data(n_units=200, n_periods=12,
+                                cohort_periods=[4, 6, 8], seed=42)
+
+# Fit stacked DiD with event study
+est = StackedDiD(kappa_pre=2, kappa_post=2)
+results = est.fit(data, outcome='outcome', unit='unit',
+                  time='period', first_treat='first_treat',
+                  aggregate='event_study')
+results.print_summary()
+
+# Access stacked data for custom analysis
+stacked = results.stacked_data
+
+# Convenience function
+from diff_diff import stacked_did
+results = stacked_did(data, 'outcome', 'unit', 'period', 'first_treat',
+                      kappa_pre=2, kappa_post=2, aggregate='event_study')
+```
+
+**Parameters:**
+
+```python
+StackedDiD(
+    kappa_pre=1,                          # Pre-treatment event-study periods
+    kappa_post=1,                         # Post-treatment event-study periods
+    weighting='aggregate',                # 'aggregate', 'population', or 'sample_share'
+    clean_control='not_yet_treated',      # 'not_yet_treated', 'strict', or 'never_treated'
+    cluster='unit',                       # 'unit' or 'unit_subexp'
+    alpha=0.05,                           # Significance level
+    anticipation=0,                       # Anticipation periods
+    rank_deficient_action='warn',         # 'warn', 'error', or 'silent'
+)
+```
+
+> **Note:** Group aggregation (`aggregate='group'`) is not supported because the pooled
+> stacked regression cannot produce cohort-specific effects. Use `CallawaySantAnna` or
+> `ImputationDiD` for cohort-level estimates.
+
+**When to use Stacked DiD vs Callaway-Sant'Anna:**
+
+| Aspect | Stacked DiD | Callaway-Sant'Anna |
+|--------|-------------|-------------------|
+| Approach | Stack cohort sub-experiments, run pooled TWFE | 2x2 DiD aggregation |
+| Symmetric windows | Enforced via kappa_pre / kappa_post | Not required |
+| Control group | Not-yet-treated (default) or never-treated | Never-treated or not-yet-treated |
+| Covariates | Passed to pooled regression | Doubly robust / IPW |
+| Intuition | Familiar event-study regression | Nonparametric aggregation |
+
+**Convenience function:**
+
+```python
+# One-liner estimation
+results = stacked_did(
+    data,
+    outcome='outcome',
+    unit='unit',
+    time='period',
+    first_treat='first_treat',
+    kappa_pre=3,
+    kappa_post=3,
+    aggregate='event_study'
+)
+```
+
 ### Triple Difference (DDD)
 
 Triple Difference (DDD) is used when treatment requires satisfying two criteria: belonging to a treated **group** AND being in an eligible **partition**. The `TripleDifference` class implements the methodology from Ortiz-Villavicencio & Sant'Anna (2025), which correctly handles covariate adjustment (unlike naive implementations).
@@ -2241,6 +2316,60 @@ TwoStageDiD(
 | `print_summary(alpha)` | Print summary to stdout |
 | `to_dataframe(level)` | Convert to DataFrame ('observation', 'event_study', 'group') |
 
+### StackedDiD
+
+```python
+StackedDiD(
+    kappa_pre=1,                          # Pre-treatment event-study periods
+    kappa_post=1,                         # Post-treatment event-study periods
+    weighting='aggregate',                # 'aggregate', 'population', or 'sample_share'
+    clean_control='not_yet_treated',      # 'not_yet_treated', 'strict', or 'never_treated'
+    cluster='unit',                       # 'unit' or 'unit_subexp'
+    alpha=0.05,                           # Significance level
+    anticipation=0,                       # Anticipation periods
+    rank_deficient_action='warn',         # 'warn', 'error', or 'silent'
+)
+```
+
+**fit() Parameters:**
+
+| Parameter | Type | Description |
+|-----------|------|-------------|
+| `data` | DataFrame | Panel data |
+| `outcome` | str | Outcome variable column name |
+| `unit` | str | Unit identifier column |
+| `time` | str | Time period column |
+| `first_treat` | str | First treatment period column (0 for never-treated) |
+| `population` | str, optional | Population column (required if weighting='population') |
+| `aggregate` | str | Aggregation: None, `"simple"`, or `"event_study"` |
+
+### StackedDiDResults
+
+**Attributes:**
+
+| Attribute | Description |
+|-----------|-------------|
+| `overall_att` | Overall average treatment effect on the treated |
+| `overall_se` | Standard error |
+| `overall_t_stat` | T-statistic |
+| `overall_p_value` | P-value for H0: ATT = 0 |
+| `overall_conf_int` | Confidence interval |
+| `event_study_effects` | Dict of relative time -> effect dict (if `aggregate='event_study'`) |
+| `stacked_data` | The stacked dataset used for estimation |
+| `n_treated_obs` | Number of treated observations |
+| `n_untreated_obs` | Number of untreated (clean control) observations |
+| `n_cohorts` | Number of treatment cohorts |
+| `kappa_pre` | Pre-treatment window used |
+| `kappa_post` | Post-treatment window used |
+
+**Methods:**
+
+| Method | Description |
+|--------|-------------|
+| `summary(alpha)` | Get formatted summary string |
+| `print_summary(alpha)` | Print summary to stdout |
+| `to_dataframe(level)` | Convert to DataFrame ('event_study') |
+
 ### TripleDifference
 
 ```python
@@ -2727,6 +2856,8 @@ The `HonestDiD` module implements sensitivity analysis methods for relaxing the
 
 - **Goodman-Bacon, A. (2021).** "Difference-in-Differences with Variation in Treatment Timing." *Journal of Econometrics*, 225(2), 254-277. [https://doi.org/10.1016/j.jeconom.2021.03.014](https://doi.org/10.1016/j.jeconom.2021.03.014)
 
+- **Wing, C., Freedman, S. M., & Hollingsworth, A. (2024).** "Stacked Difference-in-Differences." *NBER Working Paper* 32054. [https://www.nber.org/papers/w32054](https://www.nber.org/papers/w32054)
+
 ### Power Analysis
 
 - **Bloom, H. S. (1995).** "Minimum Detectable Effects: A Simple Way to Report the Statistical Power of Experimental Designs." *Evaluation Review*, 19(5), 547-556. [https://doi.org/10.1177/0193841X9501900504](https://doi.org/10.1177/0193841X9501900504)

{diff_diff-2.4.3 → diff_diff-2.6.0}/README.md

@@ -70,7 +70,7 @@ Signif. codes: '***' 0.001, '**' 0.01, '*' 0.05, '.' 0.1
 - **Wild cluster bootstrap**: Valid inference with few clusters (<50) using Rademacher, Webb, or Mammen weights
 - **Panel data support**: Two-way fixed effects estimator for panel designs
 - **Multi-period analysis**: Event-study style DiD with period-specific treatment effects
-- **Staggered adoption**: Callaway-Sant'Anna (2021), Sun-Abraham (2021), Borusyak-Jaravel-Spiess (2024) imputation, and Two-Stage DiD (Gardner 2022) estimators for heterogeneous treatment timing
+- **Staggered adoption**: Callaway-Sant'Anna (2021), Sun-Abraham (2021), Borusyak-Jaravel-Spiess (2024) imputation, Two-Stage DiD (Gardner 2022), and Stacked DiD (Wing, Freedman & Hollingsworth 2024) estimators for heterogeneous treatment timing
 - **Triple Difference (DDD)**: Ortiz-Villavicencio & Sant'Anna (2025) estimators with proper covariate handling
 - **Synthetic DiD**: Combined DiD with synthetic control for improved robustness
 - **Triply Robust Panel (TROP)**: Factor-adjusted DiD with synthetic weights (Athey et al. 2025)
@@ -100,6 +100,9 @@ We provide Jupyter notebook tutorials in `docs/tutorials/`:
 | `08_triple_diff.ipynb` | Triple Difference (DDD) estimation with proper covariate handling |
 | `09_real_world_examples.ipynb` | Real-world data examples (Card-Krueger, Castle Doctrine, Divorce Laws) |
 | `10_trop.ipynb` | Triply Robust Panel (TROP) estimation with factor model adjustment |
+| `11_imputation_did.ipynb` | Imputation DiD (Borusyak et al. 2024), pre-trend test, efficiency comparison |
+| `12_two_stage_did.ipynb` | Two-Stage DiD (Gardner 2022), GMM sandwich variance, per-observation effects |
+| `13_stacked_did.ipynb` | Stacked DiD (Wing et al. 2024), Q-weights, sub-experiment inspection, trimming, clean control definitions |
 
 ## Data Preparation
 
@@ -974,6 +977,78 @@ TwoStageDiD(
 
 Both estimators are the efficient estimator under homogeneous treatment effects, producing shorter confidence intervals than Callaway-Sant'Anna or Sun-Abraham.
 
+### Stacked DiD (Wing, Freedman & Hollingsworth 2024)
+
+Stacked DiD addresses TWFE bias in staggered adoption settings by constructing a "clean" comparison dataset for each treatment cohort and stacking them together. Each cohort's sub-experiment compares units treated at that cohort's timing against units that are not yet treated (or never treated) within a symmetric event-study window. This avoids the "bad comparisons" problem in TWFE while retaining a regression-based framework that practitioners familiar with event studies will find intuitive.
+
+```python
+from diff_diff import StackedDiD, generate_staggered_data
+
+# Generate sample data
+data = generate_staggered_data(n_units=200, n_periods=12,
+                                cohort_periods=[4, 6, 8], seed=42)
+
+# Fit stacked DiD with event study
+est = StackedDiD(kappa_pre=2, kappa_post=2)
+results = est.fit(data, outcome='outcome', unit='unit',
+                  time='period', first_treat='first_treat',
+                  aggregate='event_study')
+results.print_summary()
+
+# Access stacked data for custom analysis
+stacked = results.stacked_data
+
+# Convenience function
+from diff_diff import stacked_did
+results = stacked_did(data, 'outcome', 'unit', 'period', 'first_treat',
+                      kappa_pre=2, kappa_post=2, aggregate='event_study')
+```
+
+**Parameters:**
+
+```python
+StackedDiD(
+    kappa_pre=1,                          # Pre-treatment event-study periods
+    kappa_post=1,                         # Post-treatment event-study periods
+    weighting='aggregate',                # 'aggregate', 'population', or 'sample_share'
+    clean_control='not_yet_treated',      # 'not_yet_treated', 'strict', or 'never_treated'
+    cluster='unit',                       # 'unit' or 'unit_subexp'
+    alpha=0.05,                           # Significance level
+    anticipation=0,                       # Anticipation periods
+    rank_deficient_action='warn',         # 'warn', 'error', or 'silent'
+)
+```
+
+> **Note:** Group aggregation (`aggregate='group'`) is not supported because the pooled
+> stacked regression cannot produce cohort-specific effects. Use `CallawaySantAnna` or
+> `ImputationDiD` for cohort-level estimates.
+
+**When to use Stacked DiD vs Callaway-Sant'Anna:**
+
+| Aspect | Stacked DiD | Callaway-Sant'Anna |
+|--------|-------------|-------------------|
+| Approach | Stack cohort sub-experiments, run pooled TWFE | 2x2 DiD aggregation |
+| Symmetric windows | Enforced via kappa_pre / kappa_post | Not required |
+| Control group | Not-yet-treated (default) or never-treated | Never-treated or not-yet-treated |
+| Covariates | Passed to pooled regression | Doubly robust / IPW |
+| Intuition | Familiar event-study regression | Nonparametric aggregation |
+
+**Convenience function:**
+
+```python
+# One-liner estimation
+results = stacked_did(
+    data,
+    outcome='outcome',
+    unit='unit',
+    time='period',
+    first_treat='first_treat',
+    kappa_pre=3,
+    kappa_post=3,
+    aggregate='event_study'
+)
+```
+
 ### Triple Difference (DDD)
 
 Triple Difference (DDD) is used when treatment requires satisfying two criteria: belonging to a treated **group** AND being in an eligible **partition**. The `TripleDifference` class implements the methodology from Ortiz-Villavicencio & Sant'Anna (2025), which correctly handles covariate adjustment (unlike naive implementations).
@@ -2203,6 +2278,60 @@ TwoStageDiD(
 | `print_summary(alpha)` | Print summary to stdout |
 | `to_dataframe(level)` | Convert to DataFrame ('observation', 'event_study', 'group') |
 
+### StackedDiD
+
+```python
+StackedDiD(
+    kappa_pre=1,                          # Pre-treatment event-study periods
+    kappa_post=1,                         # Post-treatment event-study periods
+    weighting='aggregate',                # 'aggregate', 'population', or 'sample_share'
+    clean_control='not_yet_treated',      # 'not_yet_treated', 'strict', or 'never_treated'
+    cluster='unit',                       # 'unit' or 'unit_subexp'
+    alpha=0.05,                           # Significance level
+    anticipation=0,                       # Anticipation periods
+    rank_deficient_action='warn',         # 'warn', 'error', or 'silent'
+)
+```
+
+**fit() Parameters:**
+
+| Parameter | Type | Description |
+|-----------|------|-------------|
+| `data` | DataFrame | Panel data |
+| `outcome` | str | Outcome variable column name |
+| `unit` | str | Unit identifier column |
+| `time` | str | Time period column |
+| `first_treat` | str | First treatment period column (0 for never-treated) |
+| `population` | str, optional | Population column (required if weighting='population') |
+| `aggregate` | str | Aggregation: None, `"simple"`, or `"event_study"` |
+
+### StackedDiDResults
+
+**Attributes:**
+
+| Attribute | Description |
+|-----------|-------------|
+| `overall_att` | Overall average treatment effect on the treated |
+| `overall_se` | Standard error |
+| `overall_t_stat` | T-statistic |
+| `overall_p_value` | P-value for H0: ATT = 0 |
+| `overall_conf_int` | Confidence interval |
+| `event_study_effects` | Dict of relative time -> effect dict (if `aggregate='event_study'`) |
+| `stacked_data` | The stacked dataset used for estimation |
+| `n_treated_obs` | Number of treated observations |
+| `n_untreated_obs` | Number of untreated (clean control) observations |
+| `n_cohorts` | Number of treatment cohorts |
+| `kappa_pre` | Pre-treatment window used |
+| `kappa_post` | Post-treatment window used |
+
+**Methods:**
+
+| Method | Description |
+|--------|-------------|
+| `summary(alpha)` | Get formatted summary string |
+| `print_summary(alpha)` | Print summary to stdout |
+| `to_dataframe(level)` | Convert to DataFrame ('event_study') |
+
 ### TripleDifference
 
 ```python
@@ -2689,6 +2818,8 @@ The `HonestDiD` module implements sensitivity analysis methods for relaxing the
 
 - **Goodman-Bacon, A. (2021).** "Difference-in-Differences with Variation in Treatment Timing." *Journal of Econometrics*, 225(2), 254-277. [https://doi.org/10.1016/j.jeconom.2021.03.014](https://doi.org/10.1016/j.jeconom.2021.03.014)
 
+- **Wing, C., Freedman, S. M., & Hollingsworth, A. (2024).** "Stacked Difference-in-Differences." *NBER Working Paper* 32054. [https://www.nber.org/papers/w32054](https://www.nber.org/papers/w32054)
+
 ### Power Analysis
 
 - **Bloom, H. S. (1995).** "Minimum Detectable Effects: A Simple Way to Report the Statistical Power of Experimental Designs." *Evaluation Review*, 19(5), 547-556. [https://doi.org/10.1177/0193841X9501900504](https://doi.org/10.1177/0193841X9501900504)

{diff_diff-2.4.3 → diff_diff-2.6.0}/diff_diff/__init__.py

@@ -70,6 +70,7 @@ from diff_diff.prep import (
     aggregate_to_cohorts,
     balance_panel,
     create_event_time,
+    generate_continuous_did_data,
     generate_did_data,
     generate_ddd_data,
     generate_event_study_data,
@@ -107,6 +108,11 @@ from diff_diff.two_stage import (
     TwoStageDiDResults,
     two_stage_did,
 )
+from diff_diff.stacked_did import (
+    StackedDiD,
+    StackedDiDResults,
+    stacked_did,
+)
 from diff_diff.sun_abraham import (
     SABootstrapResults,
     SunAbraham,
@@ -117,6 +123,11 @@ from diff_diff.triple_diff import (
     TripleDifferenceResults,
     triple_difference,
 )
+from diff_diff.continuous_did import (
+    ContinuousDiD,
+    ContinuousDiDResults,
+    DoseResponseCurve,
+)
 from diff_diff.trop import (
     TROP,
     TROPResults,
@@ -148,7 +159,7 @@ from diff_diff.datasets import (
     load_mpdta,
 )
 
-__version__ = "2.4.3"
+__version__ = "2.6.0"
 __all__ = [
     # Estimators
     "DifferenceInDifferences",
@@ -156,11 +167,13 @@ __all__ = [
     "MultiPeriodDiD",
     "SyntheticDiD",
     "CallawaySantAnna",
+    "ContinuousDiD",
     "SunAbraham",
     "ImputationDiD",
     "TwoStageDiD",
     "TripleDifference",
     "TROP",
+    "StackedDiD",
     # Bacon Decomposition
     "BaconDecomposition",
     "BaconDecompositionResults",
@@ -175,6 +188,8 @@ __all__ = [
     "CallawaySantAnnaResults",
     "CSBootstrapResults",
     "GroupTimeEffect",
+    "ContinuousDiDResults",
+    "DoseResponseCurve",
     "SunAbrahamResults",
     "SABootstrapResults",
     "ImputationDiDResults",
@@ -187,6 +202,8 @@ __all__ = [
     "triple_difference",
     "TROPResults",
     "trop",
+    "StackedDiDResults",
+    "stacked_did",
     # Visualization
     "plot_event_study",
     "plot_group_effects",
@@ -220,6 +237,7 @@ __all__ = [
     "generate_ddd_data",
     "generate_panel_data",
     "generate_event_study_data",
+    "generate_continuous_did_data",
     "create_event_time",
     "aggregate_to_cohorts",
     "rank_control_units",