SpikeSlabPosterior: Updates posteriors from a fit-object and a spike-and-slab...

In markvdwiel/ShrinkBayes: Bayesian analysis of high-dimensional omics data, either Gaussian or counts

Updates posteriors from a fit-object and a spike-and-slab prior

Description

Updates posteriors using a spike-and-slab prior.

Usage

SpikeSlabUpdatePosterior(fitall,fitall0, p0est,  modus="fixed", shrinkpara=NULL, shrinklc=NULL, ncpus=1,only0=FALSE)

Arguments

fitall	A 2-component list object resulting from FitAllShrink or from CombinePosteriors.
fitall0	An optional 2-component list object resulting from FitAllShrink containing the fits under the null-model.
p0est	Numeric. Estimate for fraction of null-hypotheses, usually obtained from SpikeSlabPrior
modus	Character string. Either "fixed", "random" or "logdisp". Type of variable for which the posterior is desired.
shrinkpara	Character or character vector. Name(s) of the variable(s) for which the posterior is desired. Corresponding variable can be a factor.
shrinklc	Character string. Name of the linear combination for which the posterior is desired.
ncpus	Integer. The number of cpus to use for parallel computations.
only0	Boolean. If TRUE, the function only computes the posterior probability of the null-model.

Details

This function allows one to use spike-and-slab priors, which usually results in a conservative False Discovery Rate estimate.

Value

A list object with the same number of components as the first component of fitall (number of fits), each containing 3-component lists which contain

postbetanon0	Continuous component of the posterior (as matrix)
postbeta0	Point mass (often zero) mixture proportion
loglik	Marginal log-likelihood

Author(s)

Mark A. van de Wiel

See Also

SpikeSlabPrior for computing the proportion of null-hypotheses.

markvdwiel/ShrinkBayes documentation built on March 27, 2022, 7:47 p.m.