epmx.bnpostmcmc.list: Edge probabilities matrix.

In rjbgoudie/structmcmc: Structural inference for Bayesian Networks and Variable Selection.

Description

Computes the edge probabilities and return a matrix with these. The format of the matrix is designed for the plotting function splom.epmx.

Usage

  ## S3 method for class 'bnpostmcmc.list'
 epmx(x, method = "online",
    nbin = floor((end - start + 1)/100), start = 1,
    end = length(x[[1]]), verbose = F, ...)

Arguments

x	An object of class "bnpostmcmc.list"
method	Either "online", or "offline". For online, the edge totals kept online will be used. This
nbin	The number of equally-sized bins into which the samples are divided into before computing the edge probabilities of each. This applies only for method = "offline".
start	An integer of length 1, specifying the amount of burn-in. The samples start:end inclusive will be used.
end	An integer of length 1, specifying the number of samples at the end to ignore. The samples start:end inclusive will be used.
verbose	Should progress be shown? A logical.
...	Further arguments (unused)

Details

For a problem with k nodes, the output will have k^2 columns and nbin rows. Columns are in order 1->1, 1->2, 1->3, ...., 2->1, 2->2 etc

Value

An object of class "epmx", a matrix of the form described above.

See Also

epmx, splom.epmx, splom.bnpostmcmc.list

rjbgoudie/structmcmc documentation built on Nov. 3, 2020, 3:41 a.m.