Optimal-Partitioning Inequalities in Classification and Multi-Hypotheses Testing
Hill, Theodore P. ; Tong, Y. L.
Ann. Statist., Tome 17 (1989) no. 1, p. 1325-1334 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
Optimal-partitioning and minimax risk inequalities are obtained for the classification and multi-hypotheses testing problems. Best possible bounds are derived for the minimax risk for location parameter families, based on the tail concentrations and Levy concentrations of the distributions. Special attention is given to continuous distributions with the maximum likelihood ratio property and to symmetric unimodal continuous distributions. Bounds for general (including discontinuous) distributions are also obtained.
Publié le : 1989-09-14
Classification:  Optimal-partitioning inequalities,  minimax risk,  classification and discriminant analysis,  multi-hypotheses testing,  convexity theorem,  concentration function,  tail concentration,  60E15,  62H30,  28B05 
@article{1176347272,
     author = {Hill, Theodore P. and Tong, Y. L.},
     title = {Optimal-Partitioning Inequalities in Classification and Multi-Hypotheses Testing},
     journal = {Ann. Statist.},
     volume = {17},
     number = {1},
     year = {1989},
     pages = { 1325-1334},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176347272}
}

Hill, Theodore P.; Tong, Y. L. Optimal-Partitioning Inequalities in Classification and Multi-Hypotheses Testing. Ann. Statist., Tome 17 (1989) no. 1, pp.  1325-1334. http://gdmltest.u-ga.fr/item/1176347272/