Bayesian SEM for Specification Search Problems in Testing Factorial Invariance.
Multivariate Behav Res
; 52(4): 430-444, 2017.
Article
em En
| MEDLINE
| ID: mdl-28429965
ABSTRACT
Specification search problems refer to two important but under-addressed issues in testing for factorial invariance how to select proper reference indicators and how to locate specific non-invariant parameters. In this study, we propose a two-step procedure to solve these issues. Step 1 is to identify a proper reference indicator using the Bayesian structural equation modeling approach. An item is selected if it is associated with the highest likelihood to be invariant across groups. Step 2 is to locate specific non-invariant parameters, given that a proper reference indicator has already been selected in Step 1. A series of simulation analyses show that the proposed method performs well under a variety of data conditions, and optimal performance is observed under conditions of large magnitude of non-invariance, low proportion of non-invariance, and large sample sizes. We also provide an empirical example to demonstrate the specific procedures to implement the proposed method in applied research. The importance and influences are discussed regarding the choices of informative priors with zero mean and small variances. Extensions and limitations are also pointed out.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Análise Fatorial
/
Modelos Estatísticos
Tipo de estudo:
Prognostic_studies
/
Risk_factors_studies
Limite:
Adult
/
Aged
/
Female
/
Humans
/
Male
/
Middle aged
Idioma:
En
Revista:
Multivariate Behav Res
Ano de publicação:
2017
Tipo de documento:
Article