localization

The localization procedure to detect change-points.

Provides efficient functions for detecting multiple change points in multidimensional time series. The models can be piecewise constant or polynomial. Adaptive threshold selection methods are available, see Fan and Wu (2024)	<arXiv:2403.00600>.

Xinyuan Fan 

Multiple Change-Point Detection in Multivariate Time Series

Weichi Wu 

localization function

<dl><dt>data</dt>
<dd>A numeric matrix of observations with each horizontal axis being time, and each column being the multivariate time series</dd>
<dt>intervals</dt>
<dd>A numeric matrix of intervals with each row be a vector representing the interval</dd>
<dt>l</dt>
<dd>A non-negative integer of order of polynomial (<code>l=0</code> means piecewise constant)</dd>
<dt>scaling</dt>
<dd>A logical scalar representing whether to perform refinement for locally stationary data. Only useful when <code>l=0</code></dd>
<dt>q</dt>
<dd>A positive integer of norm</dd></dl>

Arguments

Localization procedure — localization

<dl>

<dt>data</dt>
<dd>A numeric matrix of observations with each horizontal axis being time, and each column being the multivariate time series</dd>


<dt>intervals</dt>
<dd>A numeric matrix of intervals with each row be a vector representing the interval</dd>


<dt>l</dt>
<dd>A non-negative integer of order of polynomial (<code>l=0</code> means piecewise constant)</dd>


<dt>scaling</dt>
<dd>A logical scalar representing whether to perform refinement for locally stationary data. Only useful when <code>l=0</code></dd>


<dt>q</dt>
<dd>A positive integer of norm</dd>

</dl>

localization: Localization procedure

Description

Usage

Value

Arguments

Examples