mbic.penalty: Modified Bayes Information Criterion penalty term

In wbs: Wild Binary Segmentation for Multiple Change-Point Detection

Description

The function evaluates the penalty term for the Modified Bayes Information Criterion proposed in N. Zhang and D. Siegmund (2007). This routine is typically not called directly by the user; its name can be passed as an argument to changepoints.

Usage

mbic.penalty(n, cpt)

Arguments

n	the number of observations
cpt	a vector with localisations of change-points

Value

the penalty term

3/2 * k * log(n)+1/2 * sum_i^k+1 log(l_i)/n,

where k denotes the number of elements in cpt and l_i are the lengths of the intervals between changepoints in cpt

References

N. Zhang and D. Siegmund (2007), A modified Bayes information criterion with applications to the analysis of comparative genomic hybridization data, Biometrics.

Examples

x <- rnorm(300) + c(rep(1,50),rep(0,250))
w <- wbs(x)
w.cpt <- changepoints(w,penalty="mbic.penalty")
w.cpt$cpt.ic

Example output

$mbic.penalty
[1] 52

wbs documentation built on May 15, 2019, 1:04 a.m.