R/JAGS-bridge-posterior.R
bridgesampling_object.RdCreates a marginal-likelihood result from a supplied scalar natural-log marginal likelihood. This is useful for analytically known or deliberately zero-evidence models that were not evaluated by bridge sampling.
bridgesampling_object(logml = -Inf)scalar natural-log marginal likelihood. Defaults to -Inf,
representing intentional zero evidence (posterior model probability zero
under model averaging). Use NA only when a marginal-likelihood
computation failed: the result is flagged as failed (success = FALSE,
logml = NA) and the on_failure policy of
ensemble_inference(), models_inference(), and mix_posteriors()
applies to that model. Do not store failed bridge-sampling attempts as
-Inf unless zero evidence is scientifically intended.
A BayesTools_marglik object (with the class bridge of released
versions, so that bridgesampling::bf(), post_prob() and logml() apply)
with no repetition rows and the
"supplied_scalar" aggregation rule, or the "supplied_failure" rule for
a failed computation (logml = NA).