CONFIRMATORY FACTOR-ANALYSIS OF MULTITRAIT-MULTIMETHOD SELF-CONCEPT DATA - BETWEEN-GROUP AND WITHIN-GROUP INVARIANCE CONSTRAINTS

Authors
Citation
Hw. Marsh et Bm. Byrne, CONFIRMATORY FACTOR-ANALYSIS OF MULTITRAIT-MULTIMETHOD SELF-CONCEPT DATA - BETWEEN-GROUP AND WITHIN-GROUP INVARIANCE CONSTRAINTS, Multivariate behavioral research, 28(3), 1993, pp. 313-349
Citations number
41
Categorie Soggetti
Social Sciences, Mathematical Methods","Psychologym Experimental","Statistic & Probability","Mathematical, Methods, Social Sciences
ISSN journal
00273171
Volume
28
Issue
3
Year of publication
1993
Pages
313 - 349
Database
ISI
SICI code
0027-3171(1993)28:3<313:CFOMSD>2.0.ZU;2-K
Abstract
The purposes of the present investigation are to demonstrate extension s of the confirmatory factor analysis approach (CFA) to multitrait-mul timethod (MTMM) data and to evaluate self-other agreement on multiple dimensions of self-concept. Two studies evaluated the ability of signi ficant others to infer multiple dimensions of self-concept of universi ty students in Australia (n = 151) and in Canada (n = 941). In both st udies self-other agreement on the 13 Self Description Questionnaire II I (SDQIII) factors was higher than reported in previous research. Trad itional and CFA approaches to MTMM data demonstrated convergent and di scriminant validity. An extension of the CFA-MTMM approach examined wi thin-group invariance of responses by self and others and between grou p invariance across Australian and Canadian responses. Between-group i nvariance tests support the total invariance of CFA-MTMM solutions acr oss Australian and Canadian responses. The imposition of invariance co nstraints produced substantially more parsimonious models and apparent ly offers one practical remedy to problems of ill-defined solutions th at have plagued the CFA approach to MTMM data.