INVTR2

the proportional difference in loss functions (a naive robust R^2 coefficient).

family string specifying the name of the family of loss function to be used (current valid
options are "bisquare", "opt" and "mopt").

family

tuning parameters to be computed according to efficiency and / or breakdown
considerations. See <a rd-options="" href="/link/lmrobdet.control?package=RobStatTM&version=1.0.5" data-mini-rdoc="RobStatTM::lmrobdet.control">lmrobdet.control</a>, <a rd-options="" href="/link/bisquare?package=RobStatTM&version=1.0.5" data-mini-rdoc="RobStatTM::bisquare">bisquare</a>, <a rd-options="" href="/link/mopt?package=RobStatTM&version=1.0.5" data-mini-rdoc="RobStatTM::mopt">mopt</a>
and <a rd-options="" href="/link/opt?package=RobStatTM&version=1.0.5" data-mini-rdoc="RobStatTM::opt">opt</a>.

This function computes a robust version of the R^2 coefficient of determination.
It is used internally by <code>lmrobdetMM</code>,
and not meant to be used directly.

Companion package for the book: "Robust Statistics: Theory and Methods, second edition", <http://www.wiley.com/go/maronna/robust>. This package contains code that implements the robust estimators discussed in the recent second edition of the book above, as well as the scripts reproducing all the examples in the book.

Matias Salibian-Barrera

RobStatTM

Robust Statistics: Theory and Methods

Victor Yohai

Ricardo Maronna

Doug Martin

Gregory Brownson

Kjell Konis

Christophe Croux

Gentiane Haesbroeck

Martin Maechler

Manuel Koller

INVTR2 function

<dl><dt>RR2</dt>
<dd>the proportional difference in loss functions (a naive robust R^2 coefficient).</dd>
<dt>family</dt>
<dd>family string specifying the name of the family of loss function to be used (current valid
options are "bisquare", "opt" and "mopt").</dd>
<dt>cc</dt>
<dd>tuning parameters to be computed according to efficiency and / or breakdown
considerations. See lmrobdet.control, bisquare, mopt
and opt.</dd></dl>

Arguments

Victor Yohai, <a href="/link/victoryohai%40gmail.com?package=RobStatTM&version=1.0.5" data-mini-rdoc="RobStatTM::victoryohai@gmail.com">victoryohai@gmail.com</a>

Author

Robust R^2 coefficient of determination — INVTR2

<dl>

<dt>RR2</dt>
<dd>the proportional difference in loss functions (a naive robust R^2 coefficient).</dd>


<dt>family</dt>
<dd>family string specifying the name of the family of loss function to be used (current valid
options are "bisquare", "opt" and "mopt").</dd>


<dt>cc</dt>
<dd>tuning parameters to be computed according to efficiency and / or breakdown
considerations. See lmrobdet.control, bisquare, mopt
and opt.</dd>

</dl>

Victor Yohai, <a href='mailto:victoryohai@gmail.com'>victoryohai@gmail.com</a>

Last chance! 50% off unlimited learning

INVTR2: Robust R^2 coefficient of determination

Description

Usage

Value

Arguments

Author

Details

References