Splitcaltest

Purpose

Splits randomly ordered data into calibration and test sets.

Synopsis

z = splitcaltest(model,options); %identifies model (calibration step)

Also available in the Analysis interface via the data context menu

Description

The calibration and test data are split up under the assumption that the data were acquired in a random sequence. The split is based on the scores from the input model. If a matrix or DataSet are passed in place of a model, it is assumed to contain the scores for the data.

Inputs

• model = standard model structure from a factor-based model OR a double or DataSet object containing the scores to analyze.

Outputs

• z = a structure containing the class and classlookup table.

Options

• options = structure array with the following fields :

• plots: [ 'none' | {'final'} ] governs level of plotting

• algorithm: [ {'onion'} ]

• nonion: [ {3} ] the number of 'external layers'

• fraction: [ {0.66} ] fraction of data to be set as calibrations samples.

See Also

crossval, pca, pcr, preprocess.