Usage
mcmc.bgx(pm, mm, samplesets, probesets, numberCategories, categories, unknownProbeSeqs, numberOfUnknownProbeSeqs, numberGenesToWatch, whichGenesToWatch, whichProbesToWatch, iter, burnin, adaptive, batch_size=50, optimalAR=0.44, output, samplenames = "unknown", subsample = ifelse(iter > 1024, iter/1024, 1), seed = 192492, rundir)
Arguments
samplesets
A numeric vector specifying which condition each array belongs to. E.g. if samplesets=c(2,2), then the first two replicates belong to one condition and the last two replicates belong to another condition. If NULL, each array is assumed to belong to a different condition.
probesets
A numeric vector specifying how probes are grouped into probesets.
numberCategories
Number of probe affinity categories.
categories
A numeric vector specifying which category each probe belongs to.
unknownProbeSeqs
A numeric vector specifying which probes lack sequence information.
numberOfUnknownProbeSeqs
Number of probes lacking sequence information.
numberGenesToWatch
How many genes to monitor closely.
whichGenesToWatch
A numeric vector specifying which genes to monitor closely.
whichProbesToWatch
The starting position for each probe in each gene to monitor closely.
iter
Number of post burn-in iterations.
burnin
Number of burn-in iterations.
adaptive
Use adaptive MCMC for better mixing.
batch_size
Batch size for adaptive MCMC.
optimalAR
Optimal acceptance ratio.
output
One of "minimal", "trace", "diagnostic" or "mcse".
samplenames
Vector of names for each array.
subsample
Subsampling interval.
rundir
The directory in which to place the output run directories.