hdbayes (version 0.2.0)

glm.logml.napp: Log marginal likelihood of a GLM under normalized asymptotic power prior (NAPP)

Description

Uses bridge sampling to estimate the logarithm of the marginal likelihood of a GLM under the normalized asymptotic power prior (NAPP).

Usage

glm.logml.napp(post.samples, bridge.args = NULL)

Value

The function returns a list with the following objects

model

"glm_napp"

logml

the estimated logarithm of the marginal likelihood

bs

an object of class bridge or bridge_list containing the output from using bridgesampling::bridge_sampler() to compute the logarithm of the marginal likelihood of the normalized asymptotic power prior (NAPP)

Arguments

post.samples

output from glm.napp() giving posterior samples of a GLM under the normalized asymptotic power prior (NAPP), with an attribute called 'data' which includes the list of variables specified in the data block of the Stan program.

bridge.args

a list giving arguments (other than samples, log_posterior, data, lb, and ub) to pass onto bridgesampling::bridge_sampler().

References

Ibrahim, J. G., Chen, M., Gwon, Y., and Chen, F. (2015). The power prior: Theory and applications. Statistics in Medicine, 34(28), 3724–3749.

Gronau, Q. F., Singmann, H., and Wagenmakers, E.-J. (2020). bridgesampling: An r package for estimating normalizing constants. Journal of Statistical Software, 92(10).

Examples

if (instantiate::stan_cmdstan_exists()) {
  data(actg019)
  data(actg036)
  ## take subset for speed purposes
  actg019 = actg019[1:100, ]
  actg036 = actg036[1:50, ]
  data_list = list(currdata = actg019, histdata = actg036)
  formula = cd4 ~ treatment + age + race
  family = poisson('log')
  d.napp = glm.napp(
    formula = formula, family = family,
    data.list = data_list,
    chains = 1, iter_warmup = 500, iter_sampling = 1000
  )
  glm.logml.napp(
    post.samples = d.napp,
    bridge.args = list(silent = TRUE)
  )
}