[en] Classifiers start to be used in medical application
to infer diagnosis. Their results are assessed
through either a binomial or a permutation test.
Distributions built from classification of random
data with cross-validation, did not follow the
theoretical binomial distribution, showing that
binomial test was not conservative enough. A
permutation test is thus recommended.
Research center :
GIGA CRC (Cyclotron Research Center) In vivo Imaging-Aging & Memory - ULiège
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
Noirhomme, Quentin ; Université de Liège - ULiège > Centre de recherches du cyclotron
Lesenfants, Damien ; Université de Liège - ULiège > Centre de recherches du cyclotron
Gomez, Francisco; Universidad Central de Colombia > Computer Science Department
Soddu, Andrea; University of Western Ontario > Department of Physics and Astronomy
Luxen, André ; Université de Liège - ULiège > Département de chimie (sciences) > Chimie organique de synthèse
Phillips, Christophe ; Université de Liège - ULiège > Centre de recherches du cyclotron
Laureys, Steven ; Université de Liège - ULiège > Centre de recherches du cyclotron
Language :
English
Title :
On the statistical assessment of small sample classification
Publication date :
December 2013
Event name :
Annual symposium of the IEEE EMBS & IM Benelux chapter
