spatpcaCV

Internal function: M-fold Cross-validation

internal

Provide regularized principal component analysis incorporating smoothness, sparseness and orthogonality of eigen-functions
by using the alternating direction method of multipliers algorithm (Wang and Huang, 2017, <DOI:10.1080/10618600.2016.1157483>). The
method can be applied to either regularly or irregularly spaced data, including 1D, 2D, and 3D.

Wen-Ting Wang

SpatPCA

Regularized Principal Component Analysis for Spatial Data

Hsin-Cheng Huang

spatpcaCV function

<dl><dt>sxyr</dt>
<dd>A location matrix</dd>
<dt>Yr</dt>
<dd>A data matrix</dd>
<dt>M</dt>
<dd>The number of folds for CV</dd>
<dt>K</dt>
<dd>The number of estimated eigen-functions</dd>
<dt>tau1r</dt>
<dd>A range of tau1</dd>
<dt>tau2r</dt>
<dd>A range of tau2</dd>
<dt>gammar</dt>
<dd>A range of gamma</dd>
<dt>nkr</dt>
<dd>A vector of fold numbers</dd>
<dt>maxit</dt>
<dd>A maximum number of iteration</dd>
<dt>tol</dt>
<dd>A tolerance rate</dd>
<dt>l2r</dt>
<dd>A given tau2</dd></dl>

Arguments

Internal function: M-fold Cross-validation — spatpcaCV

<dl>

<dt>sxyr</dt>
<dd>A location matrix</dd>


<dt>Yr</dt>
<dd>A data matrix</dd>


<dt>M</dt>
<dd>The number of folds for CV</dd>


<dt>K</dt>
<dd>The number of estimated eigen-functions</dd>


<dt>tau1r</dt>
<dd>A range of tau1</dd>


<dt>tau2r</dt>
<dd>A range of tau2</dd>


<dt>gammar</dt>
<dd>A range of gamma</dd>


<dt>nkr</dt>
<dd>A vector of fold numbers</dd>


<dt>maxit</dt>
<dd>A maximum number of iteration</dd>


<dt>tol</dt>
<dd>A tolerance rate</dd>


<dt>l2r</dt>
<dd>A given tau2</dd>

</dl>

spatpcaCV: Internal function: M-fold Cross-validation

Description

Usage

Value

Arguments