elpd {BayesSUR}R Documentation

expected log pointwise predictive density


Measure the prediction accuracy by the elpd (expected log pointwise predictive density). The out-of-sample predictive fit can either be estimated by Bayesian leave-one-out cross-validation (LOO) or by widely applicable information criterion (WAIC) (Vehtari et al. 2017).


elpd(object, method = "LOO")



an object of class BayesSUR


the name of the prediction accuracy index. Default is the "LOO" (Bayesian LOO estimate of out-of-sample predictive fit). The other index is the "WAIC" (widely applicable information criterion). For the HRR models, both "LOO" and "WAIC" are computed based on the multivate t-distribution of the posterior predictive rather than approximation of importance sampling.


Return the predictiion accuracy measure from an object of class BayesSUR. It is elpd.loo if the argumnet method="LOO" and elpd.WAIC if method="WAIC".


Vehtari, A., Gelman, A., Gabry, J. (2017). Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC. Statistics and Computing, 27(5): 1413–1432.


data("exampleEQTL", package = "BayesSUR")
hyperpar = list( a_w = 2 , b_w = 5 )

fit <- BayesSUR(Y = exampleEQTL[["blockList"]][[1]], 
                X = exampleEQTL[["blockList"]][[2]],
                data = exampleEQTL[["data"]], outFilePath = tempdir(),
                nIter = 100, burnin = 50, nChains = 2, gammaPrior = "hotspot",
                hyperpar = hyperpar, tmpFolder = "tmp/", output_CPO=TRUE)

## check output
# print the prediction accuracy elpd (expected log pointwise predictive density) 
# by the Bayesian LOO estimate of out-of-sample predictive fit
elpd(fit, method="LOO")

[Package BayesSUR version 2.0-1 Index]