# L1-optimal Statistical Discrimination Procedures and their Asymptotic Properties

Mathematica Applicanda (1989)

- Volume: 17, Issue: 31
- ISSN: 1730-2668

## Access Full Article

top## Abstract

top## How to cite

topWojciech Niemiro. "L1-optimal Statistical Discrimination Procedures and their Asymptotic Properties." Mathematica Applicanda 17.31 (1989): null. <http://eudml.org/doc/292679>.

@article{WojciechNiemiro1989,

abstract = {We consider the generalized Z^-norm optimization problem assuming that the joint probability distri-bution of random variables is unknown. The solution to the problem has, therefore, to be estimated from a sample. We examine a natural estimator and show its strong consistency and asymptotic normality under quite general assumptions. Certain discrimination and screening problems, formalized in decision- theoretical manner, can be solved using Z^-norm minimization procedures. We derive asymptotic expansions of risk corresponding to estimated solu-tions.},

author = {Wojciech Niemiro},

journal = {Mathematica Applicanda},

keywords = {Classification and discrimination, cluster analysis; Asymptotic distribution theory; Pattern recognition, speech recognition},

language = {eng},

number = {31},

pages = {null},

title = {L1-optimal Statistical Discrimination Procedures and their Asymptotic Properties},

url = {http://eudml.org/doc/292679},

volume = {17},

year = {1989},

}

TY - JOUR

AU - Wojciech Niemiro

TI - L1-optimal Statistical Discrimination Procedures and their Asymptotic Properties

JO - Mathematica Applicanda

PY - 1989

VL - 17

IS - 31

SP - null

AB - We consider the generalized Z^-norm optimization problem assuming that the joint probability distri-bution of random variables is unknown. The solution to the problem has, therefore, to be estimated from a sample. We examine a natural estimator and show its strong consistency and asymptotic normality under quite general assumptions. Certain discrimination and screening problems, formalized in decision- theoretical manner, can be solved using Z^-norm minimization procedures. We derive asymptotic expansions of risk corresponding to estimated solu-tions.

LA - eng

KW - Classification and discrimination, cluster analysis; Asymptotic distribution theory; Pattern recognition, speech recognition

UR - http://eudml.org/doc/292679

ER -

## NotesEmbed ?

topTo embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.