lsar {TSSS}

Decomposition of Time Interval to Stationary Subintervals

Description

Decompose time series to stationary subintervals and estimate local spectrum.

Usage

lsar(y, max.arorder = 20, ns0, plot = TRUE, ...)

Arguments

y

a univariate time series.

max.arorder

highest order of AR model.

ns0

length of basic local span.

plot

logical. If TRUE (default), local spectra are plotted.

...

graphical arguments passed to the plot method.

Value

An object of class "lsar" which has a plot method. This is a list with the following components:

model

1: pooled model is accepted.
2: switched model is accepted.

ns

number of observations of local span.

span

start points and end points of local spans.

nf

number of frequencies in computing local power spectrum.

ms

order of switched model.

sds

innovation variance of switched model.

aics

AIC of switched model.

mp

order of pooled model.

sdp

innovation variance of pooled model.

aics

AIC of pooled model.

spec

local spectrum.

tsname

the name of the univariate time series y.

References

Kitagawa, G. (2020) Introduction to Time Series Modeling with Applications in R. Chapman & Hall/CRC.

Examples

# seismic data
data(MYE1F)
lsar(MYE1F, max.arorder = 10, ns0 = 100)