predict,predictor-method: Predict Method for 'predictor' Class

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

Description

Assessment of the performance of a predictor in a test data set.

Usage

  predict(object="predictor", ...)

Arguments

object	Object of class predictor.
...	Further arguments described below.

Value

A prediction object, see prediction.object for details. Objects of this class have a method for the function plot.

Methods

object

Object of class predictor.

eset

Test set, stored in a Bioconductor ExpressionSet object.

positive

String refering to one of the two classes. Sensitivity and specificity calculations are carried out with respect to this class.

class

Specification of the column in pData(eset) that contains the class information. The default value is class="class".

ngenes

Number of features used for classification. The default value is ngenes=50.

dist

Character string specifiying the method for calculation of the distance between test samples and the centroids. Possible values are "euclidean", "angle", "center" and the default "cor".

Details

The test samples are classified to the class with the nearest centroid. For methods are available for calculation of the distance between test samples and the centroids: Euclidean distance, euclidean distance after centering, angle and Pearson correlation. Calculation of distances is executed using the internal function get.d.

See Also

fit prediction predictor

Examples

### see: help(GOLUB);

cancerclass documentation built on Nov. 8, 2020, 5:31 p.m.