summary.BayesSUR {BayesSUR} | R Documentation |
summary method for class BayesSUR
Description
Summary method for class BayesSUR
. It includes the argument matching
information, Top predictors/responses on average mPIP across all
responses/predictors, elpd estimates, MCMC specification, model
specification and hyper-parameters. The summarized number of the selected
variable corresponds to the posterior mean of the latent indicator variable
thresholding at 0.5 by default.
Usage
## S3 method for class 'BayesSUR'
summary(object, Pmax = 0.5, ...)
Arguments
object |
an object of class |
Pmax |
threshold that truncates the estimated coefficients based on thresholding the estimated latent indicator variable. Default is 0.5 |
... |
other arguments |
Value
Return a result summary from an object of class BayesSUR
,
including the CPOs, number of selected predictors with mPIP>Pmax
,
top 10 predictors on average mPIP across all responses, top 10 responses on
average mPIP across all predictors, Expected log pointwise predictive
density (elpd) estimates, MCMC specification, model specification (i.e.,
covariance prior and gamma prior) and hyper-parameters.
Examples
data(exampleEQTL, package = "BayesSUR")
hyperpar <- list(a_w = 2, b_w = 5)
set.seed(9173)
fit <- BayesSUR(
Y = exampleEQTL[["blockList"]][[1]],
X = exampleEQTL[["blockList"]][[2]],
data = exampleEQTL[["data"]], outFilePath = tempdir(),
nIter = 10, burnin = 0, nChains = 1, gammaPrior = "hotspot",
hyperpar = hyperpar, tmpFolder = "tmp/", output_CPO = TRUE
)
## check output
# show the summary information
summary(fit)