mbrier

(<code>factor()</code>)
True (observed) labels.
Must have the same levels and length as <code>response</code>.

truth

(<code>matrix()</code>)
Matrix of predicted probabilities, each column is a vector of probabilities for a
specific class label.
Columns must be named with levels of <code>truth</code>.

prob

(<code>any</code>)
Additional arguments. Currently ignored.

Brier score for multi-class classification problems with $r$ labels defined as $$
 \frac{1}{n} \sum_{i=1}^n \sum_{j=1}^r (I_{ij} - p_{ij})^2.
$$
$I_{ij}$ is 1 if observation $i$ has true label $j$, and 0 otherwise.
Note that there also is the more common definition of the Brier score for binary
classification problems in <code><a rd-options="=bbrier" href="/link/bbrier()?package=mlr3measures&version=0.3.1&to=%3Dbbrier" data-mini-rdoc="=bbrier::bbrier()">bbrier()</a></code>.

Implements multiple performance measures for
supervised learning.  Includes over 40 measures for regression and
classification. Additionally, meta information about the performance
measures can be queried, e.g. what the best and worst possible
performances scores are.

Michel Lang

mlr3measures

Performance Measures for 'mlr3'

Martin Binder

mbrier function

<ul>
<li>Type: <code>"classif"</code></li>
<li>Range: $[0, 2]$</li>
<li>Minimize: <code>TRUE</code></li>
<li>Required prediction: <code>prob</code></li>
</ul>

Meta Information

Brier score for multi-class classification problems with $r$ labels defined as $$
 \frac{1}{n} \sum_{i=1}^n \sum_{j=1}^r (I_{ij} - p_{ij})^2.
$$
$I_{ij}$ is 1 if observation $i$ has true label $j$, and 0 otherwise.
Note that there also is the more common definition of the Brier score for binary
classification problems in <code><a rd-options='=bbrier' href='bbrier()'>bbrier()</a></code>.

mbrier: Multiclass Brier Score

Description

Usage

Arguments

Value

Meta Information

References

See Also

Examples