A pseudo maximum likelihood approach to inference about hierarchically structured data / Milorad S. Kovacevic and Shesh N. Rai. : CS11-613/2000-4E-PDF

"An application of the pseudo maximum likelihood method is demonstrated on estimation for a mixed linear model fitted to the dependent observations coming from a hierarchical population. This approach provides a closed form solution for estimating the parameters of the mixed linear models which seems to be simpler than the iterative procedures such as iterative probability weighted least squares method of Pfeffermann et al. (1998) . We also discuss some issues relating to model and sample design hierarchies and their impact on estimation. A small simulation study showed that the proposed procedure is efficient even for small sample sizes at higher levels"--Summary.

Lien permanent pour cette publication :
publications.gc.ca/pub?id=9.839040&sl=1

Renseignements sur la publication
Ministère/Organisme Canada. Statistics Canada. Methodology Branch.
Titre A pseudo maximum likelihood approach to inference about hierarchically structured data / Milorad S. Kovacevic and Shesh N. Rai.
Titre de la série Working paper ; 2000-4
Type de publication Série - Voir l'enregistrement principal
Langue [Anglais]
Format Électronique
Document électronique
Note(s) Digitized edition from print [produced by Statistics Canada].
"SSMD-2000-004E."
"April 2000."
Includes bibliographic references.
Summary in French.
Information sur la publication [Ottawa] : Statistics Canada, 2000.
Auteur / Contributeur Kovacevic, Milorad S.
Rai, Shesh Nath,1960-
Description 28 p. : figures.
Numéro de catalogue
  • CS11-613/2000-4E-PDF
Numéro de catalogue du ministère 11-613E no. 2000-04
Descripteurs Methodology
Statistical analysis
Demander des formats alternatifs
Pour demander une publication dans un format alternatif, remplissez le formulaire électronique des publications du gouvernement du Canada. Utilisez le champ du formulaire «question ou commentaire» pour spécifier la publication demandée.
Date de modification :