prior_predictive_check
prior_predictive_check(
data,
distribution,
number_of_draws=1000,
sample_size=None,
seed=12345,
)Prior predictive check: sample from the model priors, simulate, summarize.
Wraps the shared C++ PriorPredictiveCheck.
Parameters
| Name | Type | Description | Default |
|---|---|---|---|
| data | array_like | Observations defining the model dataset. | required |
| distribution | str | Distribution family name. | required |
| number_of_draws | int | Number of prior draws. | 1000 |
| sample_size | int | Simulated dataset size per draw; when omitted, uses len(data). |
None |
| seed | int | PRNG seed. | 12345 |
Returns
| Name | Type | Description |
|---|---|---|
| dict | number_of_valid_draws and the predictive quantile summaries (summary_mean_quantiles etc., each the [2.5, 25, 50, 75, 97.5]% quantiles). |