Comparison of methods for generalized linear mixed models parameters estimation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F17%3A00316350" target="_blank" >RIV/68407700:21340/17:00316350 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Comparison of methods for generalized linear mixed models parameters estimation

Popis výsledku v původním jazyce

During the last few years generalized linear mixed models have been increasingly used to solve a large variety of problems ranging from medical research to insurance. GLMMs are an extension of generalized linear models that contain both fixed and random effects (hence mixed models). After the idea of these models is presented, the logistic regression model, which is a member of this group of models that is used in small area estimation, is focused on. Two methods of parameter estimation are used, namely the EM algorithm and the PQL method, and they are compared by means of a simulation experiment. The properties of parameter estimates obtained by the respective methods is then studied with respect to increasing data contamination.

Název v anglickém jazyce

Comparison of methods for generalized linear mixed models parameters estimation

Popis výsledku anglicky

During the last few years generalized linear mixed models have been increasingly used to solve a large variety of problems ranging from medical research to insurance. GLMMs are an extension of generalized linear models that contain both fixed and random effects (hence mixed models). After the idea of these models is presented, the logistic regression model, which is a member of this group of models that is used in small area estimation, is focused on. Two methods of parameter estimation are used, namely the EM algorithm and the PQL method, and they are compared by means of a simulation experiment. The properties of parameter estimates obtained by the respective methods is then studied with respect to increasing data contamination.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

50403 - Social topics (Women´s and gender studies; Social issues; Family studies; Social work)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

SPMS 2017 - Stochastic and Physical Monitoring Systems, Proceedings of the international conference

ISBN

978-80-01-06338-5

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

41-47

Název nakladatele

Česká technika - nakladatelství ČVUT

Místo vydání

Praha

Místo konání akce

Dobřichovice

Datum konání akce

19. 6. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000425554500006