A frequency domain generalization of the classical quadratic discrimin
ant function was applied to the problem of classifying alpha-band mult
ichannel electroencephalogram recordings in three task conditions. The
data consisted of 41-channel recordings obtained in eyes closed, verb
al, and spatial task conditions. Classifier performance was measured b
y deriving a decision rule from a training sample of 42 recordings and
then applying the obtained rule to a test sample of 46 recordings. Th
e proportion of correct classification was .93 in the training sample
and .85 in the test sample. The classifier performed better when based
on the complete cross-spectral matrix than when restricted to power s
pectrum variables. Classification based on a subset of 16 leads reduce
d the overall proportion of correct classification to .79 in the train
ing sample and to .70 in the test sample.