dstem {dSTEM}

Detection of change points based on 'dSTEM' algorithm

Description

Detection of change points based on 'dSTEM' algorithm

Usage

dstem(
  data,
  type = c("I", "II-step", "II-linear", "mixture"),
  gamma = 20,
  alpha = 0.05
)

Arguments

data

vector of data sequence

type

"I" if the change points are piecewise linear and continuous; "II-step" if the change points are piecewise constant and noncontinuous; "II-linear" if the change points are piecewise linear and noncontinuous; "mixture" if both type I and type II change points are include in data

gamma

bandwidth of Gaussian kernel

alpha

global significant level

Value

if type is 'mixture', the output is a list of type I and type II change points, otherwise, it is a list of change points

See Also

cpTest

Examples

## piecewise linear signal
l = 1200
h = seq(150,by=150,length.out=6)
jump = rep(0,7)
beta1 = c(2,-1,2.5,-3,-0.2,2.5)/50
beta1 = c(beta1,-sum(beta1*(c(h[1],diff(h))))/(l-tail(h,1)))
signal = gen.signal(l,h,jump,beta1)
noise = rnorm(length(signal),0,1)
gamma = 25
model = dstem(signal + noise,"I",gamma=gamma,alpha=0.05)
## piecewise constant
l = 1200
h = seq(150,by=150,length.out=6)
jump = c(0,1.5,2,2.2,1.8,2,1.5)
beta1 = rep(0,length(h)+1)
signal = gen.signal(l,h,jump,beta1)
noise = rnorm(length(signal),0,1)
gamma = 25
model = dstem(signal + noise, "II-step",gamma,alpha=0.05)
## piecewise linear with jump
l = 1200
h = seq(150,by=150,length.out=6)
jump = c(0,1.5,2,2.2,1.8,2,1.5)*3
beta1 = c(2,-1,2.5,-3,-0.2,2.5,-0.5)/50
signal = gen.signal(l=l,h=h,jump=jump,b1=beta1)
noise = rnorm(length(signal),0,1)
gamma = 25
model = dstem(signal + noise, "II-linear",gamma,alpha=0.05)