Rényiho statistika pro testování hypotéz o s výběrech

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F07%3A04146161" target="_blank" >RIV/68407700:21340/07:04146161 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Rényi statistics for testing hypotheses with s samples

Popis výsledku v původním jazyce

This paper considers the problem of testing composite hypotheses about parameters of s independent samples of different sizes. It introduces Rényi's statistics, which are based on the family of Rényi's divergences between likelihoods. Under standard regularity assumptions, the asymptotic distributions of the proposed test statistics and of the likelihood ratio statistic are derived for this problem. This is applied to testing the homogeneity of variances in a problem with data from families belonging todifferent populations. The small sample performance of several members of the Rényi's family of statistics is compared with that of the likelihood ratio test by means of simulated significance levels and powers.

Název v anglickém jazyce

Rényi statistics for testing hypotheses with s samples

Popis výsledku anglicky

This paper considers the problem of testing composite hypotheses about parameters of s independent samples of different sizes. It introduces Rényi's statistics, which are based on the family of Rényi's divergences between likelihoods. Under standard regularity assumptions, the asymptotic distributions of the proposed test statistics and of the likelihood ratio statistic are derived for this problem. This is applied to testing the homogeneity of variances in a problem with data from families belonging todifferent populations. The small sample performance of several members of the Rényi's family of statistics is compared with that of the likelihood ratio test by means of simulated significance levels and powers.

Druh

O - Ostatní výsledky

CEP obor

BB - Aplikovaná statistika, operační výzkum

OECD FORD obor

—

Projekt

—

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2007

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů