LOO Predictive Measure

Usage

loo_pred_measure(
  y = NULL,
  ypred = NULL,
  mupred = NULL,
  ylp = NULL,
  measure = .pred_measure_choices(),
  group_ids = NULL,
  model_name = NULL,
  loo = NULL,
  psis_object = NULL,
  save_psis = FALSE
)

Arguments

y: vector of observed values (n)
ypred: matrix of posterior predictive draws (S x n)
mupred: matrix of posterior point predictions (S x n)
ylp: matrix of pointwise log predictive densities (S x n)
measure: predictive metric to compute
group_ids: optional grouping ids
model_name: optional model label stored in metadata
loo: loo object, preferably fit with save_psis = TRUE
psis_object: optional psis object used to derive LOO weights
save_psis: logical; if TRUE, store the psis object in output for LOO paths

Value

Placeholder