adding hierarchical its

ARCHITECTURE.md

@@ -50,6 +50,7 @@ Instantiation fits eagerly in `__init__`: `_build_design_matrices()` → `_prepa
 | Class | Method | Backends | Notable quirk |
 |-------|--------|----------|---------------|
 | `InterruptedTimeSeries` | ITS | OLS + Bayes | 3-period design via `treatment_end_time` |
+| `HierarchicalInterruptedTimeSeries` | Hierarchical ITS | Bayes only | Multi-unit panel, per-unit launch times; `effect_type` instant/event_study/placebo/saturation |
 | `PiecewiseITS` | Segmented ITS | OLS + Bayes | Fits full series; `step()`/`ramp()` transforms |
 | `DifferenceInDifferences` | DiD | OLS + Bayes | Effect from interaction coefficient |
 | `StaggeredDifferenceInDifferences` | Staggered DiD | OLS + Bayes | Fits untreated obs only |

causalpy/__init__.py

@@ -23,6 +23,9 @@
 
 from .data import load_data
 from .experiments.diff_in_diff import DifferenceInDifferences
+from .experiments.hierarchical_interrupted_time_series import (
+    HierarchicalInterruptedTimeSeries,
+)
 from .experiments.instrumental_variable import InstrumentalVariable
 from .experiments.interrupted_time_series import InterruptedTimeSeries
 from .experiments.inverse_propensity_weighting import InversePropensityWeighting
@@ -53,6 +56,7 @@
     "EstimateEffect",
     "extract_lift_for_mmm",
     "GenerateReport",
+    "HierarchicalInterruptedTimeSeries",
     "InstrumentalVariable",
     "InterruptedTimeSeries",
     "InversePropensityWeighting",

causalpy/experiments/__init__.py

@@ -14,6 +14,7 @@
 """CausalPy experiment module."""
 
 from .diff_in_diff import DifferenceInDifferences
+from .hierarchical_interrupted_time_series import HierarchicalInterruptedTimeSeries
 from .instrumental_variable import InstrumentalVariable
 from .interrupted_time_series import InterruptedTimeSeries
 from .inverse_propensity_weighting import InversePropensityWeighting
@@ -28,6 +29,7 @@
 
 __all__ = [
     "DifferenceInDifferences",
+    "HierarchicalInterruptedTimeSeries",
     "InstrumentalVariable",
     "InterruptedTimeSeries",
     "InversePropensityWeighting",