Comparaison empirique des estimateurs des taux d'erreur en analyse discriminante

in Revue de Statistique Appliquée (2003), LI(3), 61-74

Monte Carlo experiments are performed to compare twenty estimators or error rates in discriminant analysis in the case of two populations and linear classification rule. Several distributions (normal, chi ... [more ▼]

Monte Carlo experiments are performed to compare twenty estimators or error rates in discriminant analysis in the case of two populations and linear classification rule. Several distributions (normal, chi-square and beta) have been considered. Estimators eOS (for actual and expected error rate) and eB (for optimal error rate) are the best, except for distributions very different from normal distributions. The e632 estimator is the best non parametric estimator. This estimator is better than parmetric estimators for distributions very different from normal distributions. [less ▲]

Panorama des démarches qualité: à chaque stratégie son outil.

Poster (1999)