Validity and reliability of a Fijian translation and adaptation of the Eating Disorder Examination Questionnaire

Abstract

Objective: Assessment of disordered eating has uncertain validity across culturally diverse populations. This study evaluated Eating Disorder Examination Questionnaire (EDE-Q) performance in an ethnic Fijian study population.

Method: The EDE-Q was translated, adapted, and administered to school-going Fijian adolescent females (N = 523). A subsample (n = 81) completed it again within approximately 1 week. We assessed feasibility, internal consistency, and test-retest reliability; evaluated construct validity through factor analysis and correlation with similar constructs; and examined the marginal utility of an additional question on traditional purgative use.

Results: Internal consistency reliability was adequate for the global scale and subscales (Cronbach's alpha = 0.66-0.91); retest reliability was adequate for both the languages (range of ICCs, 0.50-0.79, and of kappas, 0.46-0.81, excluding purging items). Construct validity was supported by significant correlations with measures of similar constructs. Factor analysis confirms multiple dimensions of eating disorder symptoms but suggests possible culture-specific variation in this population. The majority of respondents endorsing traditional purgative use (58%) did not endorse conventional EDE-Q items assessing purging.

Discussion: The EDE-Q is a valid measure of eating disorder pathology for ethnic Fijian adolescent females and measures a unitary underlying construct.

FIGURE 1

Loadings on each of the four factors derived from an exploratory factor analysis of the EDE-Q in an ethnic Fijian population