sliceGammaMean {BSL} | R Documentation |
Generate a random sample of gamma for the R-BSL-M method of Frazier and Drovandi (2021) using slice sampling
Description
This function updates the gamma of the R-BSL-M method of Frazier and Drovandi (2021) with a slice sampler (Neal 2003). Note this function is mainly designed for internal usage.
Usage
sliceGammaMean(
ssy,
ssx,
loglike,
gamma = numeric(length(ssy)),
tau = 1,
w = 1,
std = NULL,
maxit = 1000
)
Arguments
ssy |
The observed summary statisic. |
ssx |
A matrix of the simulated summary statistics. The number of rows is the same as the number of simulations per iteration. |
loglike |
The current log synthetic likelihood. This is computed with
function |
gamma |
The additional latent parameter to account for possible
incompatability between the model and observed summary statistic. In
“BSLmisspec” method, this is updated with a slice sampler
(Neal 2003). The default gamma implies no model misspecification
and is equivalent to the standard |
tau |
Scale (or inverse rate) parameter of the Laplace prior distribution for gamma. |
w |
Step size for the stepping out in the slice sampler. The default step size is 1. |
std |
Standard deviation of the columns of ssx. If this is not
|
maxit |
The maximum number of iteration of the stepping out and shrink steps of slice sampler. The default is 1e3. |
References
Frazier DT, Drovandi C (2021).
“Robust Approximate Bayesian Inference with Synthetic Likelihood.”
Journal of Computational and Graphical Statistics (In Press).
https://arxiv.org/abs/1904.04551.
Neal RM (2003).
“Slice sampling.”
The Annals of Statistics, 31(3), 705–767.
See Also
sliceGammaVariance
for the slice sampler of the
variance inflated target distribution.