loo package to perform efficient approximate leave-one-out cross-validation on models fit with bayesGAMComputes PSIS-LOO CV, efficient approximate leave-one-out (LOO) cross-validation for
Bayesian models using Pareto smoothed importance sampling (PSIS). This calls the implementation
from the loo package of the methods described in Vehtari, Gelman, and Gabry (2017a, 2017b).
loo_bgam(object, ...)# S4 method for bayesGAMfit
loo_bgam(object, ...)
# S4 method for array
loo_bgam(object, ...)
Object of type bayesGAMfit generated from bayesGAM.
Additional parameters to pass to pass to loo::loo
a named list of class c("psis_loo", "loo")
estimatesA matrix with two columns (Estimate, SE) and three rows
(elpd_loo, p_loo, looic). This
contains point estimates and standard errors of the expected log pointwise
predictive density (elpd_loo), the effective number of parameters
(p_loo) and the LOO information criterion looic (which is
just -2 * elpd_loo, i.e., converted to deviance scale).
pointwiseA matrix with five columns (and number of rows equal to the number of
observations) containing the pointwise contributions of the measures
(elpd_loo, mcse_elpd_loo, p_loo, looic, influence_pareto_k).
in addition to the three measures in estimates, we also report
pointwise values of the Monte Carlo standard error of elpd_loo
(mcse_elpd_loo), and statistics describing the influence of
each observation on the posterior distribution (influence_pareto_k).
These are the estimates of the shape parameter \(k\) of the
generalized Pareto fit to the importance ratios for each leave-one-out
distribution. See the pareto-k-diagnostic page for details.
diagnosticsA named list containing two vectors:
pareto_k: Importance sampling reliability diagnostics. By default,
these are equal to the influence_pareto_k in pointwise.
Some algorithms can improve importance sampling reliability and
modify these diagnostics. See the pareto-k-diagnostic page for details.
n_eff: PSIS effective sample size estimates.
psis_objectThis component will be NULL unless the save_psis argument is set to
TRUE when calling loo(). In that case psis_object will be the object
of class "psis" that is created when the loo() function calls psis()
internally to do the PSIS procedure.
Vehtari, A., Gelman, A., and Gabry, J. (2017a). Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC. Statistics and Computing. 27(5), 1413<U+2013>1432. doi:10.1007/s11222-016-9696-4 (journal version, preprint arXiv:1507.04544).
Vehtari, A., Gelman, A., and Gabry, J. (2017b). Pareto smoothed importance sampling. preprint arXiv:1507.02646
Vehtari A, Gabry J, Magnusson M, Yao Y, Gelman A (2019). <U+201C>loo: Efficient leave-one-out cross-validation and WAIC for Bayesian models.<U+201D> R package version 2.2.0, <URL: https://mc-stan.org/loo>.
# NOT RUN {
f <- bayesGAM(weight ~ np(height), data = women,
family = gaussian, iter=500, chains = 1)
loo_bgam(f)
# }
Run the code above in your browser using DataLab