predictor-class

	
An object of this class is returned by the function <code>predict(...)</code> 
and represents a nearest centroid predictor learned on a training data set.   


classes

The classification protocol starts with a feature selection step and continues with nearest-centroid classification. The accurarcy of the predictor can be evaluated using training and test set validation, leave-one-out cross-validation or in a multiple random validation protocol. Methods for calculation and visualization of continuous prediction scores allow to balance sensitivity and specificity and define a cutoff value according to clinical requirements.

Daniel Kosztyla

cancerclass

Development and validation of diagnostic tests from high-dimensional molecular data

predictor-class function

Objects can be created by the call <code>new("predictor", ...)</code>.

Objects from the Class

<dl>
    <dt><code>predictor</code>:</dt><dd>Object of class <code>"predictor"</code> </dd> <dt><code>cl</code>:</dt><dd>Character string or number specifying one of the two classes. </dd> <dt><code>method</code>:</dt><dd>Character string specifying the feature selection method that was used for predictor construction: Possible values are "cor", "student.test", "welch.test", "wilcoxon.test", "foldchange", "copa", "os", "ort", "shift", "throw".  </dd> <dt><code>hparam</code>:</dt><dd>Hyperparameter needed for some of the feature selection methods. For methods copa, ors and os: Quantile (e.g. 0.75, 0.9, 0.95) used in order to detect outliers. For methods shift and throw: the minimum number of samples in each class after applying shift or throw. </dd> <dt><code>type</code>:</dt><dd>Type of calculation. Loo (leave one out) or prediction (simple prediction). </dd> <dt><code>fdata</code>:</dt><dd>Feature annotations inherited from the training ExpressionSet.</dd> </dl> 

Slots

<code>plot</code>A plot method is only avaiable for the score "zeta" that is a linear combination of features.

Methods

An object of this class is returned by the function <code>predict(...)</code> 
and represents a nearest centroid predictor learned on a training data set.

predictor-class: Class "predictor"

Description

Arguments

Objects from the Class

Slots

Methods

See Also

Examples