Best subset glm using information criteria or cross-validation,
carried by using 'leaps' algorithm (Furnival and Wilson, 1974) <doi:10.2307/1267601>
or complete enumeration (Morgan and Tatar, 1972) <doi:10.1080/00401706.1972.10488918>.
Implements PCR and PLS using AIC/BIC.
Implements one-standard deviation rule for use with the 'caret' package.

Best Subset GLM and Regression Utilities

package-ubuntu-20.04-r-4.0.5#cran#bestglm-0.37.3

<p>The data matrix is scaled and sphered so it is orthonormal.
The Cholesky decomposition is used.
</p>

<table summary="R argblock"><tr valign="top">
<td><code>X</code></td>
<td>

<p><code>X</code> rectangular data matrix
</p>
</td>
</tr></table>

<p><code><a href="../../base/html/scale.html">scale</a></code>, 
<code><a href="NNPredict.html">NNPredict</a></code>
</p>

data(longley)
longley.x <- data.matrix(longley[, 1:6])
sphereX(longley.x)

package-ubuntu-20.04-r-4.0.5#cran#bestglm-0.37.3#docs#sphereX

sphereX

Description

Usage

Arguments

Value

Author(s)

See Also

Examples

bestglm

We don't support your browser anymore