psislw {loo} | R Documentation |
As of version 2.0.0
this function is deprecated. Please use the
psis
function for the new PSIS algorithm.
psislw(lw, wcp = 0.2, wtrunc = 3/4, cores = getOption("mc.cores", 1), llfun = NULL, llargs = NULL, ...)
lw |
A matrix or vector of log weights. For computing LOO, |
wcp |
The proportion of importance weights to use for the generalized
Pareto fit. The |
wtrunc |
For truncating very large weights to S^ |
cores |
The number of cores to use for parallelization. This defaults to
the option |
llfun, llargs |
See |
... |
Ignored when |
A named list with components lw_smooth
(modified log weights)
and pareto_k
(estimated generalized
Pareto shape parameter(s) k).
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), 1413–1432. doi:10.1007/s11222-016-9696-4. ( journal, preprint arXiv:1507.04544).
Vehtari, A., Gelman, A., and Gabry, J. (2017b). Pareto smoothed importance sampling. arXiv preprint: http://arxiv.org/abs/1507.02646/
pareto-k-diagnostic
for PSIS diagnostics.