ydist

Transform z-values t(z) such that the distribution of \(p(t(z) | x)\) approximates \(p(t(y | x)\) for type = 'dist' only

Contrast trees represent a new approach for assessing the
accuracy of many types of machine learning estimates that are not
amenable to standard (cross) validation methods; see "Contrast
trees and distribution boosting", Jerome H. Friedman (2020)
<doi:10.1073/pnas.1921562117>. In situations where inaccuracies
are detected, boosted contrast trees can often improve
performance. Functions are provided to to build such trees in
addition to a special case, distribution boosting, an assumption
free method for estimating the full probability distribution of an
outcome variable given any set of joint input predictor variable
values.

Balasubramanian Narasimhan

conTree

Contrast Trees and Boosting

Jerome Friedman

ydist function

<dl><dt>model</dt>
<dd>model object output from modtrast()</dd>
<dt>x</dt>
<dd>vector of predictor variable values for a (single) observation</dd>
<dt>z</dt>
<dd>sample of z-values drawn from \(p(z | x)\)</dd>
<dt>num</dt>
<dd>number of trees used to compute model values</dd></dl>

Arguments

Transform z-values t(z) such that the distribution of \(p(t(z) | x)\) approximates \(p(t(y | x)\) for type = 'dist' only — ydist

<dl>

<dt>model</dt>
<dd>model object output from modtrast()</dd>


<dt>x</dt>
<dd>vector of predictor variable values for a (single) observation</dd>


<dt>z</dt>
<dd>sample of z-values drawn from \(p(z | x)\)</dd>


<dt>num</dt>
<dd>number of trees used to compute model values</dd>

</dl>

ydist: Transform z-values t(z) such that the distribution of \(p(t(z) | x)\) approximates \(p(t(y | x)\) for type = 'dist' only

Description

Usage

Value

Arguments

See Also