detect.change: Change point detection

In eik4862/Subway: Time Series Analysis & Visualization

Description

Take time series data and perform change point detection. It uses cpt.mean or cpt.var from changepoint package for change point detection. If plot is TRUE, it also plots the point where the changes take place.

Usage

detect.change(data, type = c("mean", "var"), ..., plot = TRUE)

Arguments

data	Time series data whose change point is to be detected. The data should be either ts object or numeric vector.
type	Type of change to be detected. Should be one of "mean" and "var". (default = "mean")
...	Extra arguments for change point detection. Refer to cpt.mean and cpt.var.
plot	If TRUE, the chagne points will be plotted. Otherwise, not. (default = TRUE)

Value

A list containing the following elements:

change.point	Change point detection result(cpt object).
plot	ggplot object of the plot. (Returned only if plot is TRUE.)

Author(s)

Sanghyun Park, Daun Jeong, and Sehun Kim

Examples

# 228 is the station code for SNU
data <- get.subway(228)

# Change point detection in mean
detect.change(data$total, type = "mean")

# Change point detection in variance
detect.change(data$total, type = "var")

eik4862/Subway documentation built on Sept. 24, 2021, 3:39 a.m.