ChangePoints: Detect Number and Location of Change Points of Independent...

In JieGroup/offlineChange: Detect Multiple Change Points from Time Series

Description

Detect the number and locations of change points based on minimizing within segment quadratic loss and applying penalized model selection approach with restriction of largest candidate number of change points.

Usage

ChangePoints(x, point_max = 5, penalty = "bic", seg_min = 1,
  num_init = NULL, cpp = TRUE)

Arguments

x	The data to find change points.
point_max	The largest candidate number of change points.
penalty	Penalty type term. Default is "bic". Users can use other penalty term.
seg_min	Minimal segment size, must be positive integer.
num_init	The number of repetition times, in order to avoid local minimal. Default is squared root of number of observations. Must be integer.
cpp	Option to accelerate using rcpp. Default is TRUE.

Details

The K change points form K+1 segments (1 2 ... change_point(1)) ... (change_point(K) ... N).

Value

num_change_point	optimal number of change points.
change_point	location of change points.

References

J. Ding, Y. Xiang, L. Shen, and V. Tarokh, Multiple Change Point Analysis: Fast Implementation and Strong Consistency. IEEE Transactions on Signal Processing, vol. 65, no. 17, pp. 4495-4510, 2017.

Examples

a<-matrix(rnorm(40,mean=-1,sd=1),nrow=20,ncol=2)
b<-matrix(rnorm(120,mean=0,sd=1),nrow=60,ncol=2)
c<-matrix(rnorm(40,mean=1,sd=1),nrow=20,ncol=2)
x<-rbind(a,b,c)
ChangePoints(x,point_max=5)
ChangePoints(x,point_max=5,penalty="hq")

JieGroup/offlineChange documentation built on Aug. 3, 2019, 8:33 a.m.