pod.bootstrap_pod_ci

bootstrap_pod_ci(
    X,
    y,
    X_eval,
    threshold,
    model_type,
    model_params,
    bandwidth,
    dist_info,
    n_boot=1000,
    nuisance_ranges=None,
    n_jobs=None,
    feature_names=None,
    poi_names=None,
    confidence_levels=None,
    nuisance_dists=None,
    progress_callback=None,
    n_mc_samples=500,
)

Estimates Confidence Bounds for the PoD curve via Bootstrapping.

This function resamples the original data with replacement n_boot times. For each resample, it refits the Mean Model (dynamically rebuilding either a Polynomial or Kriging model), recalculates residuals, and generates a new PoD curve. If Kriging is selected, the optimizer is disabled during bootstrapping to remain computationally tractable [digiqual]: each resample reuses the fitted kernel (including its learned WhiteKernel noise level) and the full-data input scaling via build_fixed_kernel_gpr, so only the posterior mean is recomputed. [M25] Sec. 2i re-estimates the model on every resample, so this interval does not include the uncertainty in the Kriging hyperparameters. Kriging residuals for the variance model are leave-one-out residuals, matching fit_variance_model.

Parameters

Name	Type	Description	Default
model_params	Any	The polynomial degree, or for Kriging the model’s model_params_ dict (kernel, x_mean, x_std).	required