WBS.uni.nonpar {changepoints}

Wild binary segmentation for univariate nonparametric change points detection.

Description

Perform wild binary segmentation for univariate nonparametric change points detection.

Usage

WBS.uni.nonpar(Y, s, e, Alpha, Beta, N, delta, level = 0)

Arguments

Y

A numeric matrix of observations with horizontal axis being time, and vertical axis being multiple observations on each time point.

s

A integer scalar of starting index.

e

A integer scalar of ending index.

Alpha

A integer vector of starting indices of random intervals.

Beta

A integer vector of ending indices of random intervals.

N

A integer vector representing number of multiple observations on each time point.

delta

A positive integer scalar of minimum spacing.

level

Should be fixed as 0.

Value

A list with the following structure:

S

A vector of estimated change points (sorted in strictly increasing order)

Dval

A vector of values of CUSUM statistic based on KS distance

Level

A vector representing the levels at which each change point is detected

Parent

A matrix with the starting indices on the first row and the ending indices on the second row

Author(s)

Oscar Hernan Madrid Padilla, Haotian Xu

References

Padilla, Yu, Wang and Rinaldo (2021) <doi:10.1214/21-EJS1809>.

See Also

thresholdBS for obtaining change points estimation, tuneBSuninonpar for a tuning version.

Examples

Y = t(as.matrix(c(rnorm(100, 0, 1), rnorm(100, 0, 10), rnorm(100, 0, 40))))
N = rep(1, 300)
M = 20
intervals = WBS.intervals(M = M, lower = 1, upper = ncol(Y))
temp = WBS.uni.nonpar(Y, 1, 300, intervals$Alpha, intervals$Beta, N, 5)
plot.ts(t(Y))
points(x = tail(temp$S[order(temp$Dval)], 4), y = Y[,tail(temp$S[order(temp$Dval)],4)], col = "red")
thresholdBS(temp, 2)