multi.change: Generating a high-dimensional time series with multiple...

In InspectChangepoint: High-Dimensional Changepoint Estimation via Sparse Projection

Generating a high-dimensional time series with multiple changepoints

Description

The data matrix is generated via X = mu + W, where mu is the mean structure matrix that captures the changepoint locations and sparsity structure, and W is a random noise matrix having independent N(0,sigma^2) entries.

Usage

multi.change(n, p, ks, zs, varthetas, sigma = 1, overlap = 0, shape = 3)

Arguments

n	Time length of the observation
p	Dimension of the multivariate time series
ks	A vector describing the number of coordinates that undergo a change in each changepoint. If only a scalar is supplied, each changepoint will have the same number of coordinates that undergo a change.
zs	A vector describing the locations of the changepoints.
varthetas	A vector describing the root mean squared change magnitude in coordinates that undergo a change for each changepoint. If only a scalar is supplied, each changepoint will have the same signal strength value.
sigma	noise level
overlap	A number between 0 and 1. The proportion of overlap in the signal coordinates for successive changepoints.
shape	How the signal strength is distributed across signal coordinates. When shape = 0, all signal coordinates are changed by the same amount; when shape = 1, their signal strength are proportional to 1, sqrt(2), ..., sqrt(k); when shape = 2, they are proportional to 1, 2, ..., k; when shape = 3, they are proportional to 1, 1/sqrt(2), ..., 1/sqrt(k).

Value

An S3 object of the class 'hdchangeseq' is returned.

• x - The generated data matrix

• mu - The mean structure of the data matrix

See Also

plot.hdchangeseq

Examples

n <- 2000; p <- 200; ks <- 40;
zs <- c(500,1000,1500); varthetas <- c(0.1,0.15,0.2); overlap <- 0.5
obj <- multi.change(n, p, ks, zs, varthetas, overlap)
plot(obj, noise = TRUE)

InspectChangepoint documentation built on May 3, 2022, 9:07 a.m.