InterruptedTimeSeries.effect_summary#

InterruptedTimeSeries.effect_summary(window='post', direction='increase', alpha=0.05, cumulative=True, relative=True, min_effect=None, treated_unit=None, period=None)[source]#

Generate a decision-ready summary of causal effects.

For three-period designs (when treatment_end_time is provided), use the period parameter to get summaries for specific periods.

Parameters:

window (str, tuple, or slice, default="post") – Time window for analysis (ignored when period is specified for three-period design)
period ({"intervention", "post", "comparison"}, optional) –
For three-period designs, specify which period to summarize: - “intervention”: Summary for intervention period only - “post”: Summary for post-intervention period only - “comparison”: Comparative summary with persistence metrics (persistence ratio,

probability that effect persisted, HDI/CI interval comparison)
- None: Default behavior (summarizes all post-treatment data, backward compatible)
direction ({"increase", "decrease", "two-sided"}, default="increase") – Direction for tail probability calculation (PyMC only)
alpha (float, default=0.05) – Significance level for HDI/CI intervals
cumulative (bool, default=True) – Whether to include cumulative effect statistics
relative (bool, default=True) – Whether to include relative effect statistics
min_effect (float, optional) – Region of Practical Equivalence (ROPE) threshold (PyMC only)
treated_unit (str, optional) – For multi-unit experiments, specify which treated unit to analyze

Returns:

Object with .table (DataFrame) and .text (str) attributes

Return type:

EffectSummary