arviz_stats.ELPDDataLOO

class arviz_stats.ELPDDataLOO(*, elpd, se, p, n_samples, n_data_points, scale, warning, good_k, elpd_i=None, pareto_k=None, approx_posterior=False, log_weights=None, log_jacobian=None, p_loo_i=None, influence_pareto_k=None, n_eff_i=None)

PSIS-LOO-CV results returned by loo and related functions.

Also returned by loo_i, loo_approximate_posterior, loo_moment_match and reloo. Inherits the attributes of ELPDData.

Attributes:

approx_posteriorbool

True when the approximate posterior correction was applied.

log_weightsxarray.DataArray, optional

Smoothed log importance weights.

log_jacobianxarray.DataArray, optional

Log-Jacobian adjustment for variable transformations.

p_loo_ixarray.DataArray, optional

Pointwise effective number of parameters, set by reloo and loo_moment_match.

influence_pareto_kxarray.DataArray, optional

Pareto k values before moment matching, set by loo_moment_match.

n_eff_ixarray.DataArray, optional

Effective sample size per observation, set by loo_moment_match.

__init__(*, elpd, se, p, n_samples, n_data_points, scale, warning, good_k, elpd_i=None, pareto_k=None, approx_posterior=False, log_weights=None, log_jacobian=None, p_loo_i=None, influence_pareto_k=None, n_eff_i=None)

Methods

__init__(*, elpd, se, p, n_samples, ...[, ...])

Attributes

approx_posterior
elpd_i
influence_pareto_k
kind	Name of the estimator that produced the result.
log_jacobian
log_weights
n_eff_i
p_loo_i
pareto_k
elpd
se
p
n_samples
n_data_points
scale
warning
good_k