PPCResult

Result of a posterior predictive check on a fitted GAM.

Usage

Source

PPCResult(
    y_rep,
    observed,
    _stats=dict(),
)

Attributes

y_rep: NDArray

Posterior predictive draws on the response scale, shape (n, n_sim). Each column is one draw from the posterior predictive distribution (a plausible dataset the model could have generated).

observed: NDArray
Observed response values used to fit the model, shape (n,).

Attributes

Name Description
stat_names Names of the computed test statistics.

stat_names

Names of the computed test statistics.

stat_names: list[str]

Methods

Name Description
p_value() Bayesian p-value for a named test statistic.
stat() Return (observed_value, rep_values) for a named statistic.

p_value()

Bayesian p-value for a named test statistic.

Usage

Source

p_value(name)

The Bayesian p-value is the proportion of replicated datasets for which the test statistic equals or exceeds the observed value: p = P(T(y^\text{rep}) \ge T(y^\text{obs})).

Values near 0.5 indicate good calibration. Values near 0 or 1 indicate systematic discrepancy between the model and the data.

Parameters

name: str
One of "mean", "sd", "min", "max", "prop_zero".

stat()

Return (observed_value, rep_values) for a named statistic.

Usage

Source

stat(name)