loo: Return LOO information criteria

In glmmfields: Generalized Linear Mixed Models with Robust Random Fields for Spatiotemporal Modeling

Return LOO information criteria

Description

Extract the LOOIC (leave-one-out information criterion) using loo::loo().

Usage

## S3 method for class 'glmmfields'
loo(x, ...)

Arguments

x	Output from glmmfields(). Must be fit with save_log_lik = TRUE, which is not the default.
...	Arguments for loo::relative_eff() and loo::loo.array().

Examples

set.seed(1)
s <- sim_glmmfields(n_draws = 12, n_knots = 12, gp_theta = 1.5,
gp_sigma = 0.2, sd_obs = 0.2)
# options(mc.cores = parallel::detectCores()) # for parallel processing

# save_log_lik defaults to FALSE to save space but is needed for loo():
m <- glmmfields(y ~ 0, time = "time",
 lat = "lat", lon = "lon", data = s$dat,
 nknots = 12, iter = 1000, chains = 4, seed = 1,
 save_log_lik = TRUE)
loo(m)

glmmfields documentation built on Oct. 21, 2023, 1:06 a.m.