preproc

This function saves the residuals after regressing the user-defined
noise variables from the user-defined "signal" variables. Noise variables can
be nuisance regressors (such as cebral spinal fluid in fMRI), time vectors,
or any other vector that the user wishes to regress out.

internal

Time series analysis of network connectivity. Detects and visualizes change points between networks.
Methods included in the package are discussed in depth in Baek, C., Gates, K. M., Leinwand, B., Pipiras, V. (2021)
"Two sample tests for high-dimensional auto-covariances" <doi:10.1016/j.csda.2020.107067>
and Baek, C., Gampe, M., Leinwand B., Lindquist K., Hopfinger J. and Gates K. (2023)
“Detecting functional connectivity changes in fMRI data” <doi:10.1007/s11336-023-09908-7>.

Changryong Baek

detectR

Change Point Detection

Mattew Gampe

Kathleen M. Gates

Seok-Oh Jeong

Vladas Pipiras

preproc function

<dl><dt>Y</dt>
<dd>data: Y = length*dim</dd>
<dt>noise</dt>
<dd>string vector indicating which variables (columns) are regressors</dd>
<dt>signal</dt>
<dd>string vector indicating which variables to regress out the noise variables from</dd></dl>

Arguments

Optional preprocessing step for regressing out noise variables. — preproc

<dl>

<dt>Y</dt>
<dd>data: Y = length*dim</dd>


<dt>noise</dt>
<dd>string vector indicating which variables (columns) are regressors</dd>


<dt>signal</dt>
<dd>string vector indicating which variables to regress out the noise variables from</dd>

</dl>

preproc: Optional preprocessing step for regressing out noise variables.

Description

Usage

Value

Arguments