BaseExperiment.effect_summary#

abstractmethod BaseExperiment.effect_summary(*, window='post', direction='increase', alpha=0.05, cumulative=True, relative=True, min_effect=None, treated_unit=None, period=None, prefix='Post-period', response_type='expectation', **kwargs)[source]#

Generate a decision-ready summary of causal effects.

Parameters:

  • window (str, tuple, or slice, default="post") – Time window for analysis (ITS/SC only, ignored for DiD/RD): - “post”: All post-treatment time points (default) - (start, end): Tuple of start and end times (handles both datetime and integer indices) - slice: Python slice object for integer indices

  • direction ({"increase", "decrease", "two-sided"}, default="increase") – Direction for tail probability calculation (PyMC only, ignored for OLS): - “increase”: P(effect > 0) - “decrease”: P(effect < 0) - “two-sided”: Two-sided p-value, report 1-p as “probability of effect”

  • alpha (float, default=0.05) – Significance level for HDI/CI intervals (1-alpha confidence level)

  • cumulative (bool, default=True) – Whether to include cumulative effect statistics (ITS/SC only, ignored for DiD/RD)

  • relative (bool, default=True) – Whether to include relative effect statistics (% change vs counterfactual) (ITS/SC only, ignored for DiD/RD)

  • min_effect (float, optional) – Region of Practical Equivalence (ROPE) threshold (PyMC only, ignored for OLS). If provided, reports P(|effect| > min_effect) for two-sided or P(effect > min_effect) for one-sided.

  • treated_unit (str, optional) – For multi-unit experiments (Synthetic Control), specify which treated unit to analyze. If None and multiple units exist, uses first unit.

  • period ({"intervention", "post", "comparison"}, optional) – For experiments with multiple periods (e.g., three-period ITS), specify which period to summarize. Defaults to None for standard behavior.

  • prefix (str, optional) – Prefix for prose generation (e.g., “During intervention”, “Post-intervention”). Defaults to “Post-period”.

  • response_type ({"expectation", "prediction"}, default="expectation") –

    Response type to compute effect sizes (ITS/SC only, ignored for DiD/RD/RKink):

    • "expectation": Effect size HDI based on model expectation (μ). Excludes observation noise, focusing on the systematic causal effect.

    • "prediction": Effect size HDI based on posterior predictive (ŷ). Includes observation noise, showing full predictive uncertainty.

  • Note (This parameter only affects experiments where the causal effect is) – calculated as the difference between observed and predicted values (ITS, Synthetic Control). For experiments where the effect is a model coefficient (DiD, RD, RKink), the HDI is always computed from the posterior of the coefficient and this parameter is ignored.

  • kwargs (Any)

Returns:

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

Return type:

EffectSummary