Add causal inference modules (DID, RD, IV, fixest) and unify package API

Integrate pyfixest for high-dimensional fixed effects estimation via thin
wrapper module (statspai.fixest). Add Difference-in-Differences (2x2 and
Callaway-Sant'Anna), regression discontinuity, IV/2SLS, and synthetic
control modules. Introduce unified CausalResult class for all causal
methods with outreg2 compatibility. Rebrand imports from pyeconometrics
to statspai.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: brycewang-stanford

.gitignore

@@ -159,3 +159,7 @@ dmypy.json
 .Trashes
 ehthumbs.db
 Thumbs.db
+
+
+# Files
+Start Superpower for R.md

pyproject.toml

@@ -56,6 +56,9 @@ performance = [
     "jax[cpu]>=0.4.0",
     "jaxlib>=0.4.0",
 ]
+fixest = [
+    "pyfixest>=0.25.0",
+]
 plotting = [
     "matplotlib>=3.5.0",
     "seaborn>=0.11.0",

src/statspai/__init__.py

@@ -1,54 +1,58 @@
 """
 StatsPAI: The AI-powered Statistics & Econometrics Toolkit for Python
 
-This package provides tools for econometric analysis including:
-- OLS regression with robust standard errors
-- Causal Forest for heterogeneous treatment effects
-- Panel data models (IV/2SLS)
-- Time series analysis
-- Publication-ready output formatting
+Unified API for causal inference and econometrics:
 
-Basic usage:
 >>> import statspai as sp
->>> 
->>> # Traditional regression
->>> result = pe.regress("y ~ x1 + x2", data=df)
->>> result.summary()
->>> 
->>> # Causal Forest for treatment effects
->>> cf = pe.causal_forest("y ~ treatment | x1 + x2", data=df)
->>> effects = cf.effect(df[['x1', 'x2']])
->>> 
->>> # Export results
->>> pe.outreg2(result, cf, filename="results.xlsx")
+>>>
+>>> # OLS regression
+>>> result = sp.regress("y ~ x1 + x2", data=df)
+>>>
+>>> # Difference-in-Differences
+>>> result = sp.did(df, y='wage', treat='treated', time='post')
+>>>
+>>> # Staggered DID (Callaway & Sant'Anna)
+>>> result = sp.did(df, y='wage', treat='first_treat',
+...                time='year', id='worker_id')
+>>>
+>>> # Causal Forest
+>>> cf = sp.causal_forest("y ~ treatment | x1 + x2", data=df)
+>>>
+>>> # Publication-quality export
+>>> sp.outreg2(result, filename="results.xlsx")
 """
 
-from .core.results import EconometricResults
+__version__ = "0.1.0"
+__author__ = "Bryce Wang"
+__email__ = "bryce@copaper.ai"
+
+from .core.results import EconometricResults, CausalResult
 from .regression.ols import regress
+from .regression.iv import ivreg, IVRegression
 from .causal.causal_forest import CausalForest, causal_forest
+from .did import did, did_2x2, callaway_santanna
+from .rd import rdrobust, rdplot
 from .output.outreg2 import OutReg2, outreg2
 
-__version__ = "0.1.0"
-__author__ = "StatsPAI Team"
-__email__ = "contact@statspai.org"
-
 __all__ = [
+    # Core
+    "EconometricResults",
+    "CausalResult",
+    # Regression
     "regress",
-    "EconometricResults", 
+    "ivreg",
+    "IVRegression",
+    # DID
+    "did",
+    "did_2x2",
+    "callaway_santanna",
+    # RD
+    "rdrobust",
+    "rdplot",
+    # Causal Forest
     "CausalForest",
     "causal_forest",
+    # Output
     "OutReg2",
     "outreg2",
 ]
-
-__version__ = "0.1.0"
-__author__ = "Bryce Wang"
-__email__ = "your.email@example.com"
-
-from .regression.ols import regress
-from .core.results import EconometricResults
-
-__all__ = [
-    "regress",
-    "EconometricResults",
-]