Publicação

Why generalized structured component analysis is not universally preferable to structural equation modeling

Ver documento

Detalhes bibliográficos
Resumo:Generalized structured component analysis has emerged in marketing and psychometric literature as an alternative to structural equation modeling. A recent simulation study recommends that, in most cases, this analysis is preferable to structural equation modeling because it outperforms the latter when the model is misspecified. This article examines the characteristics of generalized structured component analysis and reveals that the surprising previous findings are attributable to an incomplete experimental design and an error incurred during the software implementation of generalized structured component analysis. Simulated data show that generalized structured component analysis provides inconsistent estimates. In some instances, model misspecification can nearly neutralize this inconsistency, but in others it will reinforce the inconsistency. Moreover, generalized structured component analysis is hardly suitable for mediation analysis because it substantially overestimates the direct effect. Thus, generalized structured component analysis cannot be recommended universally over structural equation modeling.
Autores principais:Henseler, Joerg
Assunto:component modeling Structural equation Model structured misspecification analysis Generalized Mediation Generalized structured component analysis Mediation Model misspecification Structural equation modeling
Ano:2012
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso aberto
Instituição associada:Universidade Nova de Lisboa
Idioma:idioma desconhecido
Origem:Repositório Institucional da UNL
Descrição
Resumo:Generalized structured component analysis has emerged in marketing and psychometric literature as an alternative to structural equation modeling. A recent simulation study recommends that, in most cases, this analysis is preferable to structural equation modeling because it outperforms the latter when the model is misspecified. This article examines the characteristics of generalized structured component analysis and reveals that the surprising previous findings are attributable to an incomplete experimental design and an error incurred during the software implementation of generalized structured component analysis. Simulated data show that generalized structured component analysis provides inconsistent estimates. In some instances, model misspecification can nearly neutralize this inconsistency, but in others it will reinforce the inconsistency. Moreover, generalized structured component analysis is hardly suitable for mediation analysis because it substantially overestimates the direct effect. Thus, generalized structured component analysis cannot be recommended universally over structural equation modeling.