postK_mk: Marginal probability of K per bin

In BayesCPclust: A Bayesian Approach for Clustering Constant-Wise Change-Point Data

Marginal probability of K per bin

Description

Marginal probability of K per bin

Usage

postK_mk(k, m0, w, M, Yn, sigma2n, cellsn, mk, Cr)

Arguments

k	A scalar for the number of changes points in a cluster
m0	A scalar for the number of positions available to define change-points positions
w	A scalar representing the minimum number of points in each interval between two change points
M	A scalar representing the number of points available for each data sequence
Yn	A vector or matrix with data sequences for a cluster
sigma2n	A vector with the variance of the data sequences in a cluster
cellsn	A vector with the indices of the data sequences in a cluster
mk	A matrix with all possible values to distribute between change points
Cr	A scalar with the number of data sequences in a cluster

Value

'postK_mk' returns a numerical value representing the non-normalized probability for a given bin, given k, and a given cluster

Note

This function is called within [postK()]. It should not be called alone.

See Also

[postK()], [gibbs_alg()]

Examples

data(data)
M <- 50; k <- 0; w <- 10;
m0 <- M - 1 -(k+1)*w
for(k in 0:2){
mk <- RcppAlgos::permuteGeneral(0:m0, k + 1,
constraintFun = "sum",
comparisonFun = "==", limitConstraints = m0,
repetition = TRUE)}
out <- postK_mk(k = 0, m0 = m0, w = 10, M = 50, Yn = data[,c(1,2,4)],
 sigma2n = rep(0.05, 3), cellsn = c(1,2,4), mk = mk[1,], Cr = 3)

BayesCPclust documentation built on April 4, 2025, 5:19 a.m.