The plsdof package provides Degrees of Freedom estimates
for Partial Least Squares (PLS) Regression. Model selection for
PLS is based on various information criteria (aic, bic, gmdl)
or on cross-validation. Estimates for the mean and covariance
of the PLS regression coefficients are available. They allow
the construction of approximate confidence intervals and the
application of test procedures (Kramer and Sugiyama
2012 <doi:10.1198/jasa.2011.tm10107>).
Further, cross-validation procedures for Ridge Regression and
Principal Components Regression are available.

Degrees of Freedom and Statistical Inference for Partial Least
Squares Regression

package-ubuntu-20.04-r-4.0.5#cran#plsdof-0.3-0

<p>This function computes the trace of a matrix.
</p>

<table summary="R argblock"><tr valign="top">
<td><code>M</code></td>
<td>
<p>square matrix</p>
</td>
</tr></table>

package-ubuntu-20.04-r-4.0.5#cran#plsdof-0.3-0#docs#tr

tr

Description

Usage

Arguments

Value

Author(s)

Examples

plsdof

We don't support your browser anymore