Talk
The impact of population heterogeneity on factor analysis estimation
Catarina Marques (Marques, C.); José G. Dias (Dias, J. G.);
Event Title
XXI Jornadas de Classificação e Análise de Dados (JOCLAD2014)
Year (definitive publication)
2014
Language
English
Country
Portugal
More Information
Web of Science®

This publication is not indexed in Web of Science®

Scopus

This publication is not indexed in Scopus

Google Scholar

Times Cited: 0

(Last checked: 2024-11-17 12:59)

View record in Google Scholar

Abstract
This paper discusses the impact of population heterogeneity on factor analysis under the homogeneity assumption and potential biases resulting from aggregation. An illustration using the Holzinger-Swineford Mental Abilities data shows that the factor mixture model relaxes factor analysis specification taking population heterogeneity and potential outliers into account.
Acknowledgements
--
Keywords
Mixture factor models, Unobserved heterogeneity, Outliers detection.