2010
DOI: 10.1080/15305050903352065
|View full text |Cite
|
Sign up to set email alerts
|

Factorial Invariance Testing and Latent Mean Differences for the Self-Description Questionnaire II (Short Version) with Indigenous and Non-Indigenous Australian Secondary School Students

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

3
24
0

Year Published

2012
2012
2018
2018

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 30 publications
(27 citation statements)
references
References 41 publications
3
24
0
Order By: Relevance
“…Table 3 presents the cross‐cultural invariance testing on the latent factors only (academic self‐concept, multiculturation, discrimination, disengagement, and self‐sabotage). From these results, it can be seen that the minimal requirements for invariance are met with regard to model 2 with the acceptable fit indices (Cheung & Rensvold, 2002); less than ±0.01 change in the CFI (Cheung & Rensvold, 2002); and overlap in the 90% confidence interval of the RMSEA (Bodkin‐Andrews, Ha, et al., 2010). Model 3, although failing to meet the change in the CFI criteria, did see acceptable fit indices and overlap in the confidence interval for the RMSEA.…”
Section: Resultsmentioning
confidence: 93%
See 2 more Smart Citations
“…Table 3 presents the cross‐cultural invariance testing on the latent factors only (academic self‐concept, multiculturation, discrimination, disengagement, and self‐sabotage). From these results, it can be seen that the minimal requirements for invariance are met with regard to model 2 with the acceptable fit indices (Cheung & Rensvold, 2002); less than ±0.01 change in the CFI (Cheung & Rensvold, 2002); and overlap in the 90% confidence interval of the RMSEA (Bodkin‐Andrews, Ha, et al., 2010). Model 3, although failing to meet the change in the CFI criteria, did see acceptable fit indices and overlap in the confidence interval for the RMSEA.…”
Section: Resultsmentioning
confidence: 93%
“…Generally, TLI and CFI values close to 0.95, and RMSEA values close to 0.05, reflect relatively good fit to the data (Hu & Bentler, 1999). For the factorial invariance testing, we used a change of no more than 0.01 in the CFI and overlap in the 90% confidence interval of the RMSEA to test equivalence across groups (Bodkin‐Andrews, Ha, et al., 2010; Marsh, Tracey, & Craven, 2006).…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…Before discussing the results of the longitudinal and cross sectional data, it is important to point out that the 10 dimensions analyzed in this study obtained low correlations ( r = .19), which demonstrates an important degree of independence consistent with some previous research. However, in those studies the correlations found are a little higher: ranging from .08 to .44 (Bodkin‐Andrews, Ha, Craven, & Yeung, ) with Indigenous and non‐Indigenous Australian adolescents; from .34 and .31 in Australian and Chinese samples (Leung, Marsh, Craven, & Abduljabbar, ); or with a median value of .23 (Marsh et al., ) with high school students from Australia.…”
Section: Discussionmentioning
confidence: 95%
“…Although strong CFA results allow a substantially increased level of confidence that the measurement instruments may be valid in their measurement properties, it does not answer whether the measurement instruments mean the same thing across different groups (Bodkin-Andrews, Ha, et al, 2010). As a result, factorial invariance testing was conducted, and the criteria of no more than a +/-.01 change in the CFI (when compared to the baseline model), and overlap in the 90% confidence interval of the RMSEA was utilized Cheung & Rensvold, 2002) across increasingly restrictive models (Model 1 = baseline model with no restrictions; Model 1 factor loadings invariant across groups; Model 3 factor loadings and intercepts invariant across groups).…”
Section: Aim 1: Creating the Foundation -Psychometric Validitymentioning
confidence: 99%