Assessing the factor structure and measurement invariance of the eating attitude test (EAT-26) across language and BMI in young Arab women

Table 5 Goodness-of-fit for the EAT-19 5-factor CFI models for entire sample and across different groups of language and BMI categories in Sample 2

	Descriptions	χ² (df)	CFI	TLI	RMSEA	SRMR	CDC
CFA in Sample 2
(N = 1112)	19 items, 5-factor solution^a	854.624 (142)	0.913	0.895	0.067	0.060	0.999
CFA by Language
Arabic (n = 867)	19 items, 5-factor solution^a	742.618 (141)	0.907	0.887	0.070	0.063	0.999
English (n = 245)	19 items, 5-factor solution^a	334.104 (142)	0.900	0.879	0.074	0.066	0.999
CFA by BMI
Underweight (n = 122)	19 items, 5-factor solution^a	238.954 (142)	0.851	0.821	0.075	0.076	0.998
Normal (n = 517)	19 items, 5-factor solution^a	375.021 (142)	0.928	0.913	0.056	0.050	0.999
Overweight or Obese (n = 346)	19 items, 5-factor solution^b	447.522(142)	0.858	0.829	0.079	0.075	1.000

Note. CFA confirmatory factor analysis, CFI comparative fit index, TLI Tucker-Lewis index, CI confidence interval, RMSEA Root Mean Square Error of Approximation; Ref model is the reference model for the measurement invariance comparison; χ² = Chi-squared Statistic, df = degrees of freedom
^aAll items had loadings ≥0.40
^bAll items had loadings ≥0.40 except item “Other people think I am too thin”