PlaceboInTime.plot_calibration#

static PlaceboInTime.plot_calibration(check_result, title='Placebo-in-Time calibration', figsize=(7.0, 9.0))[source]#

Plot the three-panel calibration diagnostic for a placebo run.

Panel A shows the per-fold cumulative impact posteriors, panel B the hierarchical status-quo null pooled from them, and panel C the null against the actual effect.

Parameters:

check_result (CheckResult) – Result returned by run(). Everything the panels need is read from its metadata.
title (str) – Figure suptitle.
figsize (tuple[float, float]) – Size of the drawn figure, in inches.

Returns:

The drawn composition. When the run produced no null model, a single annotated panel is returned instead and a warning is emitted.

Return type:

matplotlib.figure.Figure