Construct validity, dimensionality and factorial invariance of the Rosenberg Self-Esteem Scale: a bifactor modelling approach among children of prisoners

Abstract

background The Rosenberg Self-Esteem Scale (RSES) has traditionally been conceptualised as a unidimensional measure of self-esteem, but empirical evidence is equivocal, with some studies supporting a one-factor solution and others favouring multidimensional models. participants and procedureThe aim of this study was to examine the factor structure, factorial invariance and composite reliability of the RSES within a European sample of children affected by parental imprisonment (N = 724). The study specified and tested six alternative factor models using conventional confirmatory factor analytic (CFA) techniques and a confirmatory bifactor modelling approach. resultsThe RSES was most effectively represented by a bifactor model including a general self-esteem factor comprising all ten scale items and separate method effects for the positively and negatively phrased items. This model was found to be factorially invariant among boys and girls. Composite reliability indicated good internal consistency for the general self-esteem dimension but slightly less so for the positive and negative method effects. conclusionsIt follows that the calculation of a total RSES score is appropriate for children of prisoners, providing that the presence of method effects is taken into consideration to avoid giving rise to false interpretations. This study demonstrated the application of a bifactorial modeling approach as a potential solution.key words Rosenberg Self-Esteem Scale (RSES); bifactor modelling; confirmatory factor analysis; factorial invariance; children of prisoners Construct validity, dimensionality and factorial invariance of the Rosenberg Self-Esteem Scale: a bifactor modelling approach among children of prisoners corresponding author

Is the Bifactor Model a Better Model or Is It Just Better at Modeling Implausible Responses? Application of Iteratively Reweighted Least Squares to the Rosenberg Self-Esteem Scale

“…One approach to addressing that question is to use a bifactor structural representation where the general factor represents the substantive trait and the group factors represent method artifacts associated with item wording (see Hyland, Boduszek, Dhingra, Shevlin, & Egan, 2014; McKay, Boduszek, & Harvey, 2014; Sharratt, Boduszek, Jones, & Gallagher, 2014). These studies suggest that the RSES is essentially unidimensional once controlling for the effects of direction of wording (e.g., Donnellan, Ackerman, & Brecheen, 2016); moreover, problems appear localized to the negatively-worded items (Corwyn, 2000; Marsh, 1996).…”

Construct Validity and Dimensionality of the Rosenberg Self-Esteem Scale and Its Association with Spiritual Values Within Irish Population

“…Recent debate is centred on its use as an all-inclusive construct or as a twofold variable scheme. The studies of Debowska et al (2017), Sharratt et al (2014), Boduszek et al (2013), and Boduszek et al (2012) suggest that the twofold structure is a more appropriate manner of applying RSES in social studies. Recent research applying the bifactorial modelling also confirmed the two-dimensional nature of the self-esteem construct (Hyland et al 2014;McKay et al 2014).…”

Who is a dangerous driver? Socio-demographic and personal determinants of risky traffic behavior

“…The Rosenberg Self-esteem Scale (SES) adapted by Dzwonkowska, Lachowicz-Tabaczek and Łaguna (2008) measures global self-esteem in adolescents and adults (Sharratt, Boduszek, Jones, & Gallagher, 2014). The reliability of the Polish adaptation measured with Cronbach's α for different standardization groups -as well as for the entire sample -ranges between .81 and .83.…”