cpd {copent}

Single change point detection with copula entropy based two-sample test

Description

Single change point detection with copula entropy based two-sample test.

Usage

cpd(x,thd=0.13,n=15,k=3,dt=2,ncores=0)

Arguments

x

data with each row as a sample of d-dimensional random variables

thd

threshold of the statistic of two-sample test for detecting a change point, default = 0.13

n

the argument used by two-sample test, default = 15

k

kth nearest neighbour, default = 3

dt

the type of distance between samples, 1 for Eclidean distance; 2 for Maximum distance. default = 2

ncores

number of cores to be used for parallel computing, default = 0 for all the cores

Details

This program involves detecting single change point in univariate or multivariate time series data with copula entropy based two-sample test. It was proposed in Ma (2024), in which a group of two-sample tests are performed on time series data and the change point is considered to be associated with the maximum of the statistics of all the tests.

The argument x is for the data with each row as a sample of d-dimensional random variables. The argument thd is for the threshold of the statistic of two-sample test for detecting a change point. If the maximum of the statistics of all the two-sample tests is below the threshold, no change point is detected. The argument n is the argument used by the two-sample test function tst. The argument k and dt is used in the kNN method for estimating entropy. k is for the kth nearest neighbour (default = 3) and dt is for the type of distance between samples which has currently two value options (1 for Eclidean distance, and 2(default) for Maximum distance). The argument ncores is for the number of cores to be used for parallel computing. If the default 0 is used, then all the cores will be used.

Value

The function returns a list containing

stats

the estimated statistics of all the two-sample tests

maxstat

the maximum of the estimated statistics

pos

the change point detected

References

Ma, Jian. Change Point Detection with Copula Entropy based Two-Sample Test. arXiv preprint arXiv:2403.07892, 2024.

Examples

x = c(rnorm(15,0,1),rnorm(15,0,10))
cpd(x,thd=0.15,ncores=2)