diff-diff 0.3.0__tar.gz → 0.4.0__tar.gz

{diff_diff-0.3.0 → diff_diff-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: diff-diff
-Version: 0.3.0
+Version: 0.4.0
 Summary: A library for Difference-in-Differences causal inference analysis
 Author: diff-diff contributors
 License-Expression: MIT
@@ -104,7 +104,10 @@ Signif. codes: '***' 0.001, '**' 0.01, '*' 0.05, '.' 0.1
 - **Robust inference**: Heteroskedasticity-robust (HC1) and cluster-robust standard errors
 - **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) estimator for heterogeneous treatment timing
 - **Synthetic DiD**: Combined DiD with synthetic control for improved robustness
+- **Event study plots**: Publication-ready visualization of treatment effects
+- **Parallel trends testing**: Multiple methods including equivalence tests
 - **Data prep utilities**: Helper functions for common data preparation tasks
 
 ## Data Preparation
@@ -342,6 +345,79 @@ cohort_data = aggregate_to_cohorts(
 # Result: mean outcome by treatment group and period
 ```
 
+### Rank Control Units
+
+Select the best control units for DiD or Synthetic DiD analysis by ranking them based on pre-treatment outcome similarity:
+
+```python
+from diff_diff import rank_control_units, generate_did_data
+
+# Generate sample data
+data = generate_did_data(n_units=50, n_periods=6, seed=42)
+
+# Rank control units by their similarity to treated units
+ranking = rank_control_units(
+    data,
+    unit_column='unit',
+    time_column='period',
+    outcome_column='outcome',
+    treatment_column='treated',
+    n_top=10  # Return top 10 controls
+)
+
+print(ranking[['unit', 'quality_score', 'pre_trend_rmse']])
+```
+
+Output:
+```
+   unit  quality_score  pre_trend_rmse
+0    35         1.0000          0.4521
+1    42         0.9234          0.5123
+2    28         0.8876          0.5892
+...
+```
+
+With covariates for matching:
+
+```python
+# Add covariate-based matching
+ranking = rank_control_units(
+    data,
+    unit_column='unit',
+    time_column='period',
+    outcome_column='outcome',
+    treatment_column='treated',
+    covariates=['size', 'age'],  # Match on these too
+    outcome_weight=0.7,          # 70% weight on outcome trends
+    covariate_weight=0.3         # 30% weight on covariate similarity
+)
+```
+
+Filter data for SyntheticDiD using top controls:
+
+```python
+from diff_diff import SyntheticDiD
+
+# Get top control units
+top_controls = ranking['unit'].tolist()
+
+# Filter data to treated + top controls
+filtered_data = data[
+    (data['treated'] == 1) | (data['unit'].isin(top_controls))
+]
+
+# Fit SyntheticDiD with selected controls
+sdid = SyntheticDiD()
+results = sdid.fit(
+    filtered_data,
+    outcome='outcome',
+    treatment='treated',
+    unit='unit',
+    time='period',
+    post_periods=[3, 4, 5]
+)
+```
+
 ## Usage
 
 ### Basic DiD with Column Names
@@ -522,6 +598,148 @@ Signif. codes: '***' 0.001, '**' 0.01, '*' 0.05, '.' 0.1
 ================================================================================
 ```
 
+### Staggered Difference-in-Differences (Callaway-Sant'Anna)
+
+When treatment is adopted at different times by different units, traditional TWFE estimators can be biased. The Callaway-Sant'Anna estimator provides unbiased estimates with staggered adoption.
+
+```python
+from diff_diff import CallawaySantAnna
+
+# Panel data with staggered treatment
+# 'first_treat' = period when unit was first treated (0 if never treated)
+cs = CallawaySantAnna()
+results = cs.fit(
+    panel_data,
+    outcome='sales',
+    unit='firm_id',
+    time='year',
+    first_treat='first_treat',  # 0 for never-treated, else first treatment year
+    aggregate='event_study'      # Compute event study effects
+)
+
+# View results
+results.print_summary()
+
+# Access group-time effects ATT(g,t)
+for (group, time), effect in results.group_time_effects.items():
+    print(f"Cohort {group}, Period {time}: {effect['effect']:.3f}")
+
+# Event study effects (averaged by relative time)
+for rel_time, effect in results.event_study_effects.items():
+    print(f"e={rel_time}: {effect['effect']:.3f} (SE: {effect['se']:.3f})")
+
+# Convert to DataFrame
+df = results.to_dataframe(level='event_study')
+```
+
+Output:
+```
+=====================================================================================
+          Callaway-Sant'Anna Staggered Difference-in-Differences Results
+=====================================================================================
+
+Total observations:                     600
+Treated units:                           35
+Control units:                           15
+Treatment cohorts:                        3
+Time periods:                             8
+Control group:                never_treated
+
+-------------------------------------------------------------------------------------
+                  Overall Average Treatment Effect on the Treated
+-------------------------------------------------------------------------------------
+Parameter         Estimate     Std. Err.     t-stat      P>|t|   Sig.
+-------------------------------------------------------------------------------------
+ATT                 2.5000       0.3521       7.101     0.0000   ***
+-------------------------------------------------------------------------------------
+
+95% Confidence Interval: [1.8099, 3.1901]
+
+-------------------------------------------------------------------------------------
+                          Event Study (Dynamic) Effects
+-------------------------------------------------------------------------------------
+Rel. Period       Estimate     Std. Err.     t-stat      P>|t|   Sig.
+-------------------------------------------------------------------------------------
+0                   2.1000       0.4521       4.645     0.0000   ***
+1                   2.5000       0.4123       6.064     0.0000   ***
+2                   2.8000       0.5234       5.349     0.0000   ***
+-------------------------------------------------------------------------------------
+
+Signif. codes: '***' 0.001, '**' 0.01, '*' 0.05, '.' 0.1
+=====================================================================================
+```
+
+**When to use Callaway-Sant'Anna vs TWFE:**
+
+| Scenario | Use TWFE | Use Callaway-Sant'Anna |
+|----------|----------|------------------------|
+| All units treated at same time | ✓ | ✓ |
+| Staggered adoption, homogeneous effects | ✓ | ✓ |
+| Staggered adoption, heterogeneous effects | ✗ | ✓ |
+| Need event study with staggered timing | ✗ | ✓ |
+| Fewer than ~20 treated units | ✓ | Depends on design |
+
+**Parameters:**
+
+```python
+CallawaySantAnna(
+    control_group='never_treated',  # or 'not_yet_treated'
+    anticipation=0,                  # Periods before treatment with effects
+    estimation_method='dr',          # 'dr', 'ipw', or 'reg'
+    alpha=0.05,                      # Significance level
+    cluster=None,                    # Column for cluster SEs
+    n_bootstrap=0,                   # Must be 0 (bootstrap not yet implemented)
+    seed=None                        # Random seed
+)
+```
+
+**Current limitations:**
+- Bootstrap inference (`n_bootstrap > 0`) is not yet implemented
+- Covariate adjustment for conditional parallel trends is not yet implemented
+
+### Event Study Visualization
+
+Create publication-ready event study plots:
+
+```python
+from diff_diff import plot_event_study, MultiPeriodDiD, CallawaySantAnna
+
+# From MultiPeriodDiD
+did = MultiPeriodDiD()
+results = did.fit(data, outcome='y', treatment='treated',
+                  time='period', post_periods=[3, 4, 5])
+plot_event_study(results, title="Treatment Effects Over Time")
+
+# From CallawaySantAnna (with event study aggregation)
+cs = CallawaySantAnna()
+results = cs.fit(data, outcome='y', unit='unit', time='period',
+                 first_treat='first_treat', aggregate='event_study')
+plot_event_study(results, title="Staggered DiD Event Study")
+
+# From a DataFrame
+df = pd.DataFrame({
+    'period': [-2, -1, 0, 1, 2],
+    'effect': [0.1, 0.05, 0.0, 2.5, 2.8],
+    'se': [0.3, 0.25, 0.0, 0.4, 0.45]
+})
+plot_event_study(df, reference_period=0)
+
+# With customization
+ax = plot_event_study(
+    results,
+    title="Dynamic Treatment Effects",
+    xlabel="Years Relative to Treatment",
+    ylabel="Effect on Sales ($1000s)",
+    color="#2563eb",
+    marker="o",
+    shade_pre=True,           # Shade pre-treatment region
+    show_zero_line=True,      # Horizontal line at y=0
+    show_reference_line=True, # Vertical line at reference period
+    figsize=(10, 6),
+    show=False                # Don't call plt.show(), return axes
+)
+```
+
 ### Synthetic Difference-in-Differences
 
 Synthetic DiD combines the strengths of Difference-in-Differences and Synthetic Control methods by re-weighting control units to better match treated units' pre-treatment outcomes.
@@ -1061,6 +1279,31 @@ aggregate_to_cohorts(
 )
 ```
 
+#### rank_control_units
+
+```python
+rank_control_units(
+    data,                          # Panel data in long format
+    unit_column,                   # Unit identifier column
+    time_column,                   # Time period column
+    outcome_column,                # Outcome variable column
+    treatment_column=None,         # Treatment indicator column (0/1)
+    treated_units=None,            # Explicit list of treated unit IDs
+    pre_periods=None,              # Pre-treatment periods (default: first half)
+    covariates=None,               # Covariate columns for matching
+    outcome_weight=0.7,            # Weight for outcome trend similarity (0-1)
+    covariate_weight=0.3,          # Weight for covariate distance (0-1)
+    exclude_units=None,            # Units to exclude from control pool
+    require_units=None,            # Units that must appear in output
+    n_top=None,                    # Return only top N controls
+    suggest_treatment_candidates=False,  # Identify treatment candidates
+    n_treatment_candidates=5,      # Number of treatment candidates
+    lambda_reg=0.0                 # Regularization for synthetic weights
+)
+```
+
+Returns DataFrame with columns: `unit`, `quality_score`, `outcome_trend_score`, `covariate_score`, `synthetic_weight`, `pre_trend_rmse`, `is_required`.
+
 ## Requirements
 
 - Python >= 3.9
@@ -1126,14 +1369,20 @@ This library implements methods from the following scholarly works:
 
 - **Rambachan, A., & Roth, J. (2023).** "A More Credible Approach to Parallel Trends." *The Review of Economic Studies*, 90(5), 2555-2591. [https://doi.org/10.1093/restud/rdad018](https://doi.org/10.1093/restud/rdad018)
 
+- **Lakens, D. (2017).** "Equivalence Tests: A Practical Primer for t Tests, Correlations, and Meta-Analyses." *Social Psychological and Personality Science*, 8(4), 355-362. [https://doi.org/10.1177/1948550617697177](https://doi.org/10.1177/1948550617697177)
+
 ### Multi-Period and Staggered Adoption
 
 - **Callaway, B., & Sant'Anna, P. H. C. (2021).** "Difference-in-Differences with Multiple Time Periods." *Journal of Econometrics*, 225(2), 200-230. [https://doi.org/10.1016/j.jeconom.2020.12.001](https://doi.org/10.1016/j.jeconom.2020.12.001)
 
+- **Sant'Anna, P. H. C., & Zhao, J. (2020).** "Doubly Robust Difference-in-Differences Estimators." *Journal of Econometrics*, 219(1), 101-122. [https://doi.org/10.1016/j.jeconom.2020.06.003](https://doi.org/10.1016/j.jeconom.2020.06.003)
+
 - **Sun, L., & Abraham, S. (2021).** "Estimating Dynamic Treatment Effects in Event Studies with Heterogeneous Treatment Effects." *Journal of Econometrics*, 225(2), 175-199. [https://doi.org/10.1016/j.jeconom.2020.09.006](https://doi.org/10.1016/j.jeconom.2020.09.006)
 
 - **de Chaisemartin, C., & D'Haultfœuille, X. (2020).** "Two-Way Fixed Effects Estimators with Heterogeneous Treatment Effects." *American Economic Review*, 110(9), 2964-2996. [https://doi.org/10.1257/aer.20181169](https://doi.org/10.1257/aer.20181169)
 
+- **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)
+
 ### General Causal Inference
 
 - **Imbens, G. W., & Rubin, D. B. (2015).** *Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction*. Cambridge University Press.

{diff_diff-0.3.0 → diff_diff-0.4.0}/README.md

@@ -69,7 +69,10 @@ Signif. codes: '***' 0.001, '**' 0.01, '*' 0.05, '.' 0.1
 - **Robust inference**: Heteroskedasticity-robust (HC1) and cluster-robust standard errors
 - **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) estimator for heterogeneous treatment timing
 - **Synthetic DiD**: Combined DiD with synthetic control for improved robustness
+- **Event study plots**: Publication-ready visualization of treatment effects
+- **Parallel trends testing**: Multiple methods including equivalence tests
 - **Data prep utilities**: Helper functions for common data preparation tasks
 
 ## Data Preparation
@@ -307,6 +310,79 @@ cohort_data = aggregate_to_cohorts(
 # Result: mean outcome by treatment group and period
 ```
 
+### Rank Control Units
+
+Select the best control units for DiD or Synthetic DiD analysis by ranking them based on pre-treatment outcome similarity:
+
+```python
+from diff_diff import rank_control_units, generate_did_data
+
+# Generate sample data
+data = generate_did_data(n_units=50, n_periods=6, seed=42)
+
+# Rank control units by their similarity to treated units
+ranking = rank_control_units(
+    data,
+    unit_column='unit',
+    time_column='period',
+    outcome_column='outcome',
+    treatment_column='treated',
+    n_top=10  # Return top 10 controls
+)
+
+print(ranking[['unit', 'quality_score', 'pre_trend_rmse']])
+```
+
+Output:
+```
+   unit  quality_score  pre_trend_rmse
+0    35         1.0000          0.4521
+1    42         0.9234          0.5123
+2    28         0.8876          0.5892
+...
+```
+
+With covariates for matching:
+
+```python
+# Add covariate-based matching
+ranking = rank_control_units(
+    data,
+    unit_column='unit',
+    time_column='period',
+    outcome_column='outcome',
+    treatment_column='treated',
+    covariates=['size', 'age'],  # Match on these too
+    outcome_weight=0.7,          # 70% weight on outcome trends
+    covariate_weight=0.3         # 30% weight on covariate similarity
+)
+```
+
+Filter data for SyntheticDiD using top controls:
+
+```python
+from diff_diff import SyntheticDiD
+
+# Get top control units
+top_controls = ranking['unit'].tolist()
+
+# Filter data to treated + top controls
+filtered_data = data[
+    (data['treated'] == 1) | (data['unit'].isin(top_controls))
+]
+
+# Fit SyntheticDiD with selected controls
+sdid = SyntheticDiD()
+results = sdid.fit(
+    filtered_data,
+    outcome='outcome',
+    treatment='treated',
+    unit='unit',
+    time='period',
+    post_periods=[3, 4, 5]
+)
+```
+
 ## Usage
 
 ### Basic DiD with Column Names
@@ -487,6 +563,148 @@ Signif. codes: '***' 0.001, '**' 0.01, '*' 0.05, '.' 0.1
 ================================================================================
 ```
 
+### Staggered Difference-in-Differences (Callaway-Sant'Anna)
+
+When treatment is adopted at different times by different units, traditional TWFE estimators can be biased. The Callaway-Sant'Anna estimator provides unbiased estimates with staggered adoption.
+
+```python
+from diff_diff import CallawaySantAnna
+
+# Panel data with staggered treatment
+# 'first_treat' = period when unit was first treated (0 if never treated)
+cs = CallawaySantAnna()
+results = cs.fit(
+    panel_data,
+    outcome='sales',
+    unit='firm_id',
+    time='year',
+    first_treat='first_treat',  # 0 for never-treated, else first treatment year
+    aggregate='event_study'      # Compute event study effects
+)
+
+# View results
+results.print_summary()
+
+# Access group-time effects ATT(g,t)
+for (group, time), effect in results.group_time_effects.items():
+    print(f"Cohort {group}, Period {time}: {effect['effect']:.3f}")
+
+# Event study effects (averaged by relative time)
+for rel_time, effect in results.event_study_effects.items():
+    print(f"e={rel_time}: {effect['effect']:.3f} (SE: {effect['se']:.3f})")
+
+# Convert to DataFrame
+df = results.to_dataframe(level='event_study')
+```
+
+Output:
+```
+=====================================================================================
+          Callaway-Sant'Anna Staggered Difference-in-Differences Results
+=====================================================================================
+
+Total observations:                     600
+Treated units:                           35
+Control units:                           15
+Treatment cohorts:                        3
+Time periods:                             8
+Control group:                never_treated
+
+-------------------------------------------------------------------------------------
+                  Overall Average Treatment Effect on the Treated
+-------------------------------------------------------------------------------------
+Parameter         Estimate     Std. Err.     t-stat      P>|t|   Sig.
+-------------------------------------------------------------------------------------
+ATT                 2.5000       0.3521       7.101     0.0000   ***
+-------------------------------------------------------------------------------------
+
+95% Confidence Interval: [1.8099, 3.1901]
+
+-------------------------------------------------------------------------------------
+                          Event Study (Dynamic) Effects
+-------------------------------------------------------------------------------------
+Rel. Period       Estimate     Std. Err.     t-stat      P>|t|   Sig.
+-------------------------------------------------------------------------------------
+0                   2.1000       0.4521       4.645     0.0000   ***
+1                   2.5000       0.4123       6.064     0.0000   ***
+2                   2.8000       0.5234       5.349     0.0000   ***
+-------------------------------------------------------------------------------------
+
+Signif. codes: '***' 0.001, '**' 0.01, '*' 0.05, '.' 0.1
+=====================================================================================
+```
+
+**When to use Callaway-Sant'Anna vs TWFE:**
+
+| Scenario | Use TWFE | Use Callaway-Sant'Anna |
+|----------|----------|------------------------|
+| All units treated at same time | ✓ | ✓ |
+| Staggered adoption, homogeneous effects | ✓ | ✓ |
+| Staggered adoption, heterogeneous effects | ✗ | ✓ |
+| Need event study with staggered timing | ✗ | ✓ |
+| Fewer than ~20 treated units | ✓ | Depends on design |
+
+**Parameters:**
+
+```python
+CallawaySantAnna(
+    control_group='never_treated',  # or 'not_yet_treated'
+    anticipation=0,                  # Periods before treatment with effects
+    estimation_method='dr',          # 'dr', 'ipw', or 'reg'
+    alpha=0.05,                      # Significance level
+    cluster=None,                    # Column for cluster SEs
+    n_bootstrap=0,                   # Must be 0 (bootstrap not yet implemented)
+    seed=None                        # Random seed
+)
+```
+
+**Current limitations:**
+- Bootstrap inference (`n_bootstrap > 0`) is not yet implemented
+- Covariate adjustment for conditional parallel trends is not yet implemented
+
+### Event Study Visualization
+
+Create publication-ready event study plots:
+
+```python
+from diff_diff import plot_event_study, MultiPeriodDiD, CallawaySantAnna
+
+# From MultiPeriodDiD
+did = MultiPeriodDiD()
+results = did.fit(data, outcome='y', treatment='treated',
+                  time='period', post_periods=[3, 4, 5])
+plot_event_study(results, title="Treatment Effects Over Time")
+
+# From CallawaySantAnna (with event study aggregation)
+cs = CallawaySantAnna()
+results = cs.fit(data, outcome='y', unit='unit', time='period',
+                 first_treat='first_treat', aggregate='event_study')
+plot_event_study(results, title="Staggered DiD Event Study")
+
+# From a DataFrame
+df = pd.DataFrame({
+    'period': [-2, -1, 0, 1, 2],
+    'effect': [0.1, 0.05, 0.0, 2.5, 2.8],
+    'se': [0.3, 0.25, 0.0, 0.4, 0.45]
+})
+plot_event_study(df, reference_period=0)
+
+# With customization
+ax = plot_event_study(
+    results,
+    title="Dynamic Treatment Effects",
+    xlabel="Years Relative to Treatment",
+    ylabel="Effect on Sales ($1000s)",
+    color="#2563eb",
+    marker="o",
+    shade_pre=True,           # Shade pre-treatment region
+    show_zero_line=True,      # Horizontal line at y=0
+    show_reference_line=True, # Vertical line at reference period
+    figsize=(10, 6),
+    show=False                # Don't call plt.show(), return axes
+)
+```
+
 ### Synthetic Difference-in-Differences
 
 Synthetic DiD combines the strengths of Difference-in-Differences and Synthetic Control methods by re-weighting control units to better match treated units' pre-treatment outcomes.
@@ -1026,6 +1244,31 @@ aggregate_to_cohorts(
 )
 ```
 
+#### rank_control_units
+
+```python
+rank_control_units(
+    data,                          # Panel data in long format
+    unit_column,                   # Unit identifier column
+    time_column,                   # Time period column
+    outcome_column,                # Outcome variable column
+    treatment_column=None,         # Treatment indicator column (0/1)
+    treated_units=None,            # Explicit list of treated unit IDs
+    pre_periods=None,              # Pre-treatment periods (default: first half)
+    covariates=None,               # Covariate columns for matching
+    outcome_weight=0.7,            # Weight for outcome trend similarity (0-1)
+    covariate_weight=0.3,          # Weight for covariate distance (0-1)
+    exclude_units=None,            # Units to exclude from control pool
+    require_units=None,            # Units that must appear in output
+    n_top=None,                    # Return only top N controls
+    suggest_treatment_candidates=False,  # Identify treatment candidates
+    n_treatment_candidates=5,      # Number of treatment candidates
+    lambda_reg=0.0                 # Regularization for synthetic weights
+)
+```
+
+Returns DataFrame with columns: `unit`, `quality_score`, `outcome_trend_score`, `covariate_score`, `synthetic_weight`, `pre_trend_rmse`, `is_required`.
+
 ## Requirements
 
 - Python >= 3.9
@@ -1091,14 +1334,20 @@ This library implements methods from the following scholarly works:
 
 - **Rambachan, A., & Roth, J. (2023).** "A More Credible Approach to Parallel Trends." *The Review of Economic Studies*, 90(5), 2555-2591. [https://doi.org/10.1093/restud/rdad018](https://doi.org/10.1093/restud/rdad018)
 
+- **Lakens, D. (2017).** "Equivalence Tests: A Practical Primer for t Tests, Correlations, and Meta-Analyses." *Social Psychological and Personality Science*, 8(4), 355-362. [https://doi.org/10.1177/1948550617697177](https://doi.org/10.1177/1948550617697177)
+
 ### Multi-Period and Staggered Adoption
 
 - **Callaway, B., & Sant'Anna, P. H. C. (2021).** "Difference-in-Differences with Multiple Time Periods." *Journal of Econometrics*, 225(2), 200-230. [https://doi.org/10.1016/j.jeconom.2020.12.001](https://doi.org/10.1016/j.jeconom.2020.12.001)
 
+- **Sant'Anna, P. H. C., & Zhao, J. (2020).** "Doubly Robust Difference-in-Differences Estimators." *Journal of Econometrics*, 219(1), 101-122. [https://doi.org/10.1016/j.jeconom.2020.06.003](https://doi.org/10.1016/j.jeconom.2020.06.003)
+
 - **Sun, L., & Abraham, S. (2021).** "Estimating Dynamic Treatment Effects in Event Studies with Heterogeneous Treatment Effects." *Journal of Econometrics*, 225(2), 175-199. [https://doi.org/10.1016/j.jeconom.2020.09.006](https://doi.org/10.1016/j.jeconom.2020.09.006)
 
 - **de Chaisemartin, C., & D'Haultfœuille, X. (2020).** "Two-Way Fixed Effects Estimators with Heterogeneous Treatment Effects." *American Economic Review*, 110(9), 2964-2996. [https://doi.org/10.1257/aer.20181169](https://doi.org/10.1257/aer.20181169)
 
+- **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)
+
 ### General Causal Inference
 
 - **Imbens, G. W., & Rubin, D. B. (2015).** *Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction*. Cambridge University Press.

diff_diff-0.4.0/diff_diff/__init__.py

@@ -0,0 +1,80 @@
+"""
+diff-diff: A library for Difference-in-Differences analysis.
+
+This library provides sklearn-like estimators for causal inference
+using the difference-in-differences methodology.
+"""
+
+from diff_diff.estimators import (
+    DifferenceInDifferences,
+    TwoWayFixedEffects,
+    MultiPeriodDiD,
+    SyntheticDiD,
+)
+from diff_diff.staggered import (
+    CallawaySantAnna,
+    CallawaySantAnnaResults,
+    GroupTimeEffect,
+)
+from diff_diff.results import (
+    DiDResults,
+    MultiPeriodDiDResults,
+    PeriodEffect,
+    SyntheticDiDResults,
+)
+from diff_diff.visualization import (
+    plot_event_study,
+    plot_group_effects,
+)
+from diff_diff.prep import (
+    make_treatment_indicator,
+    make_post_indicator,
+    wide_to_long,
+    balance_panel,
+    validate_did_data,
+    summarize_did_data,
+    generate_did_data,
+    create_event_time,
+    aggregate_to_cohorts,
+    rank_control_units,
+)
+from diff_diff.utils import (
+    check_parallel_trends,
+    check_parallel_trends_robust,
+    equivalence_test_trends,
+)
+
+__version__ = "0.4.0"
+__all__ = [
+    # Estimators
+    "DifferenceInDifferences",
+    "TwoWayFixedEffects",
+    "MultiPeriodDiD",
+    "SyntheticDiD",
+    "CallawaySantAnna",
+    # Results
+    "DiDResults",
+    "MultiPeriodDiDResults",
+    "SyntheticDiDResults",
+    "PeriodEffect",
+    "CallawaySantAnnaResults",
+    "GroupTimeEffect",
+    # Visualization
+    "plot_event_study",
+    "plot_group_effects",
+    # Parallel trends testing
+    "check_parallel_trends",
+    "check_parallel_trends_robust",
+    "equivalence_test_trends",
+    # Data preparation utilities
+    "make_treatment_indicator",
+    "make_post_indicator",
+    "wide_to_long",
+    "balance_panel",
+    "validate_did_data",
+    "summarize_did_data",
+    "generate_did_data",
+    "create_event_time",
+    "aggregate_to_cohorts",
+    "rank_control_units",
+]