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.
|Author||Jan Budczies, Daniel Kosztyla|
|Date of publication||None|
|Maintainer||Daniel Kosztyla <firstname.lastname@example.org>|
cancerclass-internal: Internal Functions in the cancerclass Package
cancerclass-package: Development and validation of diagnostic tests from...
fit: Fitting of a predictor
GOLUB: GOLUB DATA
loo: Leave-one-out cross-validation
nvalidate: Classification in a multiple random validation protocol in...
nvalidation-class: Class "nvalidation"
plot: Plot Method for 'validation, nvalidation, prediction,...
plot3d: Plot3d method for 'validtion and 'nvalidation' classes
prediction-class: Class "prediction"
predictor-class: Class "predictor"
predict,predictor-method: Predict Method for 'predictor' Class
summary,prediction-method: Summary Method for 'prediction' Class
validate: Classification in a Multiple Random Validation Protocol in...
validation-class: Class "validation"