logo Idiap Research Institute        
 [BibTeX] [Marc21]
Are two Classifiers performing equally? A treatment using Bayesian Hypothesis Testing
Type of publication: Idiap-RR
Citation: barber:hypothesis:rr:04:57
Number: Idiap-RR-57-2004
Year: 2004
Month: 5
Institution: IDIAP
Address: Rue de Simplon 4, Martigny, CH-1920, Switerland
Note: IDIAP-RR 04-57
Abstract: We consider here how to assess if two classifiers, based on a set of test error results, are performing equally well. This question is often considered in the realm of sampling theory, based on classical hypothesis testing. Here we present a simple Bayesian treatment that is quite general, and also is able to deal with the (practically common) case where the errors that two classifiers make are dependent.
Userfields: ipdmembership={learning},
Keywords:
Projects Idiap
Authors Barber, David
Added by: [UNK]
Total mark: 0
Attachments
  • barber_dirichlet_test_idiap_rr.pdf
  • barber_dirichlet_test_idiap_rr.ps.gz
Notes