arviz_stats.ELPDDataLFO

class arviz_stats.ELPDDataLFO(*, elpd, se, p, n_samples, n_data_points, scale, warning, good_k, elpd_i=None, pareto_k=None, forecast_horizon, min_observations, refits, n_refits, p_lfo_i=None)

Leave-future-out cross-validation results returned by lfo_cv.

Inherits the attributes of ELPDData. n_data_points counts forecast origins.

Attributes:

forecast_horizonint

Number of steps ahead that were predicted.

min_observationsint

Minimum number of training observations.

refitsndarray

Time indices at which the model was refit.

n_refitsint

Number of refits performed.

p_lfo_ixarray.DataArray, optional

Pointwise effective number of parameters, only when pointwise=True.

__init__(*, elpd, se, p, n_samples, n_data_points, scale, warning, good_k, elpd_i=None, pareto_k=None, forecast_horizon, min_observations, refits, n_refits, p_lfo_i=None)

Methods

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

Attributes

elpd_i
kind	Name of the estimator that produced the result.
p_lfo_i
pareto_k
forecast_horizon
min_observations
refits
n_refits
elpd
se
p
n_samples
n_data_points
scale
warning
good_k