Package 'ICSS'

Title: ICSS Algorithm by Inclan/Tiao (1994)
Description: The Iterative Cumulative Sum of Squares (ICSS) algorithm by Inclan/Tiao (1994) <https://www.jstor.org/stable/2290916> detects multiple change points, i.e. structural break points, in the variance of a sequence of independent observations. For series of moderate size (i.e. 200 observations and beyond), the ICSS algorithm offers results comparable to those obtained by a Bayesian approach or by likelihood ration tests, without the heavy computational burden required by these approaches.
Authors: Siegfried Köstlmeier [aut, cre, cph]
Maintainer: Siegfried Köstlmeier <[email protected]>
License: GPL-2
Version: 1.1
Built: 2025-02-08 06:59:16 UTC
Source: CRAN

Help Index

Sample data for Inclan/Tiao (1994)

Description

Generated random data (n=700) with following the scheme in Inclan/Tiao (1994):

  • [1;390]Mean: 0; Variance: 1.000

  • [391;517]Mean: 0; Variance: 0.365

  • [518;700]Mean: 0; Variance: 1.033

Usage

data(data)

Examples

## load data
data(data)

## calculate the variance until the first breakpoint.
data_var <- var(data[1:390])

Iterative Cumulative Sum of Squares (ICSS)

Description

ICSS implements the Iterative Cumulative Sum of Squares (ICSS) algorithm by Inclan/Tiao (1994).

The test detects structural breakpoints in the variance of time series data.

Usage

ICSS(data, demean = FALSE)

Arguments

data

A numerical vector
demean

An object of class "logical": If demean is TRUE, all data will get demeaned prior to the ICSS algorithm.

Value

ICSS returns a numerical vector containing the location of structural breakpoints or NA if none breakpoints are found.

References

Inclan, C., & Tiao, G. C. (1994): Use of cumulative sums of squares for retrospective detection of changes of variance. Journal of the American Statistical Association, 89(427), 913-923. https://www.jstor.org/stable/2290916.

Examples

## load demo data
data(data)
breakpoints <- ICSS(data)