The Beck Depression Inventory (French Version): Testing for Gender-Invariant Factorial Structure for Nonclinical Adolescents

Abstract

The purposes of the study were threefold: (a) to testforthefactorial validity of the French version of the Beck Depression Inventory (BDI-FR) separatelyfornonclinical adolescent francophone males (n = 551) andfemales (n = 601), (b) to cross-validatefindings across a second independent sample for each gender, and (c) to test for equivalent factorial structure across genderfor this population. Exceptfor one differentialfactor loadingfor females (Item 17), the hypothesized higher order4-factor structure was found to be both tenable across validation samples andfactorially invariant across gender. Although the presence of error covariances for females partially replicated a similar pattern for Englishfemale adolescents, results generally provide strong supportfor the psychometric soundness of the BDI-FR.

Factorial Validity and Invariance of a Survey Measuring Psychosocial Correlates of Colorectal Cancer Screening among African Americans and Caucasians

“…Therefore, we examined the modification indices across subgroups to see how fit may be improved and found large m 2 values for two error covariances ([cc_famthk, cc_famdo] and [cc_famthk, cc_drthk]). This result indicated shared error variance among scales measuring the same construct that is a common finding among scales measuring attitudes and beliefs (60). We respecified the five-factor model by adding two error covariances and found improved fit to the data for all race-sex subgroups ( Table 3).…”

“…The second model set all factor loadings to be equal across the four groups. We conducted a global test of equality of covariance structures that computed the m 2 difference value versus the degrees of freedom (59,60). This difference test statistic follows a m 2 distribution.…”

Measuring depression for Swedish nonclinical adolescents: Factorial validity and equivalence of the Beck Depression Inventory across gender

“…Addressing this issue, Byrne et al (1993Byrne et al ( , 1994 tested these equality assumptions across Canadian adolescent males and females as they related to 2nd-order models of factor structure for both the English and French versions of the BDI, respectively. Except for a few subtle differences, they reported this hierarchical structure to be factorially invariant across gender.…”

Interpreting the results of studies using latent variable models to assess data quality: an empirical example using confirmatory factor analysis

“…These studies have shown that DIF can attenuate or accentuate group differences (Cole 1999;Huang et al 1997;Pentz and Chou 1994;Smith and Reise 1998;Waller et al 2000), lead to inaccurate diagnoses (Cole et al 1998;Gallo et al 1994;Reid et al 1998;Waller et al 2000), and generally decrease reliability and validity Byrne et al , 1994Byrne et al , 1996Byrne et al , 1998Byrne and Campbell 1999;Knight and Hill 1998;Schafer and Caetano 1996). Studies have also uncovered DIF so profound as to render cross group comparisons virtually impossible (Knight et al 1992;Prelow et al 2000).…”