blockSeg-proc: 'blockSeg' fitting procedure

In jchiquet/blockseg: Two Dimensional Change-Points Detection

Description

Produce a block-wise estimation of a matrix.

Usage

blockSeg(Y, max.break = floor(min(ncol(Y), nrow(Y))/10 + 1),
  max.var = floor(ncol(Y)^2/2), verbose = TRUE, Beta = FALSE)

Arguments

Y	matrix of observations.
max.break	a positive integer less than number of columns and number of rows. By default, floor(min(ncol(Y),nrow(Y))/10+1).
max.var	a positive integer less than number of columns times number of rows. By default, ncol(Y)**2/2.
verbose	logical. To display each step. By default TRUE.
Beta	logical. To save each Beta associated at each lambda. By default FALSE (very heavy in memory space).

Examples

 ## model parameters
n <- 100
K <- 5
mu <- suppressWarnings(matrix(rep(c(1,0),ceiling(K**2/2)), K,K))
Y <- rblockdata(n,mu,sigma=.5)$Y
res <- blockSeg(Y, 50)

jchiquet/blockseg documentation built on Aug. 30, 2019, 9:18 a.m.