simchangeslope: Generate simulated data

In grosed/cpop: Detection of Multiple Changes in Slope in Univariate Time-Series

Generate simulated data

Description

Generates simulated data for use with cpop.

Usage

simchangeslope(x, changepoints, change.slope, sd = 1)

Arguments

x	A numeric vector containing the locations of the data.
changepoints	A numeric vector of changepoint locations.
change.slope	A numeric vector indicating the change in slope at each changepoint. The initial slope is assumed to be 0.
sd	The residual standard deviation. Can be a single numerical value or a vector of values for the case of varying residual standard deviation. Default value is 1.

Value

A vector of simulated y values.

References

\insertRef

cpop-jss-article-2024cpop

Examples

library(cpop)
library(pacman)
p_load(ggplot2)

# simulate changepoints with constant sd
set.seed(1)
changepoints <- c(0,25,50,100)
change.slope <- c(0.2,-0.3,0.2,-0.1)
x <- 1:200
sd <- 0.2
y <- simchangeslope(x,changepoints,change.slope,sd)
df <- data.frame("x"=x,"y"=y)
p <- ggplot(data=df,aes(x=x,y=y))
p <- p + geom_point()
p <- p + geom_vline(xintercept=changepoints,
                    color="red",
                    linetype="dashed")
print(p)

# simulate changepoints with varying sd
sd <- 0.2 + x/200
y <- simchangeslope(x,changepoints,change.slope,sd)
df$y <- y
p <- ggplot(data=df,aes(x=x,y=y))
p <- p + geom_point()
p <- p + geom_vline(xintercept=changepoints,
                    color="red",
                    linetype="dashed")
print(p)

grosed/cpop documentation built on May 31, 2024, 11:16 a.m.