Bifactor Models and Rotations: Exploring the Extent to which Multidimensional Data Yield Univocal Scale Scores

By S. Reise, Tyler M. Moore, Mark G. Haviland. Journal of Personality Assessment, 2010

1,184 citations recorded by the source corpus.

The application of psychological measures often results in item response data that arguably are consistent with both unidimensional (a single common factor) and multidimensional latent structures (typically caused by parcels of items that tap similar content domains). As such, structural ambiguity leads to seemingly endless “confirmatory” factor analytic studies in which the research question is whether scale scores can be interpreted as reflecting variation on a single trait. An alternative to the more commonly observed unidimensional, correlated traits, or second-order representations of a measure's latent structure is a bifactor model. Bifactor structures, however, are not well understood in the personality assessment community and thus rarely are applied. To address this, herein we (a) describe issues that arise in conceptualizing and modeling multidimensionality, (b) describe exploratory (including Schmid–Leiman [Schmid & Leiman, 1957] and target bifactor rotations) and confirmatory bifactor modeling, (c) differentiate between bifactor and second-order models, and (d) suggest contexts where bifactor analysis is particularly valuable (e.g., for evaluating the plausibility of subscales, determining the extent to which scores reflect a single variable even when the data are multidimensional, and evaluating the feasibility of applying a unidimensional item response theory (IRT) measurement model). We emphasize that the determination of dimensionality is a related but distinct question from either determining the extent to which scores reflect a single individual difference variable or determining the effect of multidimensionality on IRT item parameter estimates. Indeed, we suggest that in many contexts, multidimensional data can yield interpretable scale scores and be appropriately fitted to unidimensional IRT models.

Subfields: Clinical Psychology, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/52d427baffa36aed41169acd94fdc6a68b673313

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Clinical Psychology

In Experimental and Cognitive Psychology

Citations in the corpus

Scoring and Modeling Psychological Measures in the Presence of Multidimensionality (2013, background): “In the context of other psychological measures, similar claims are made in Reise et al. (2010), Gustafsson and Aberg-Bengtsson (2010), Brown, Finney, and France (2011), and Zinbarg, Barlow, and Brown (1997).”
The Self-Compassion Scale is a Valid and Theoretically Coherent Measure of Self-Compassion (2016, methodology): “Another psychometric approach is a bi-factor model (Reise et al. 2010, 2013), which is designed to assess the multidimensionality of psychological measures.”
Protection as the Mirror Image of Psychopathology: Further Critical Notes on the Self-Compassion Scale (2016, background): “…three (nonclinical) of the five samples and the finding of a satisfactory omega test statistic (which is known to be inflated in lengthy scales containing multiple factors, like the SCS; see Reise et al. 2010), Neff concluded that there is sufficient proof to justify the use of the SCS total score.”
Factor Structure of the Difficulties in Emotion Regulation Scale (DERS) in Adult Outpatients Receiving Dialectical Behavior Therapy (DBT) (2017, methodology): “Although not formally offered as a standard, Reise et al. (2010) appeared to use .50 as a rough indicator of what constitutes a noteworthy loading on primary factors (see Table 6 and discussion on p. 555).”
The Italian version of the Depression Anxiety Stress Scales-21: Factor structure and psychometric properties on community and clinical samples. (2015, methodology): “Given that under certain conditions traditional fit indices could be biased in favor of the bifactor solution among other more parsimonious rival models [44], the hierarchical omega squared was calculated in order to have a better evaluation of the bifactor solution, not only in terms of fit indices”
Does Self-Compassion Entail Reduced Self-Judgment, Isolation, and Over-Identification? A Response to Muris, Otgaar, and Petrocchi (2016) (2016, background): “…(non-clinical) of the five samples and the finding of a satisfactory omega test statistic (which is known to be inflated in lengthy scales containing multiple factors, like the SCS; see Reise et al. 2010), Neff concluded that there is sufficient proof to justify the use of the SCS total score.”
Evaluating the Perceived Stress Scale among UK university students: implications for stress measurement and management (2019, methodology): “In situations when items load highly onto a general factor, but simultaneously load to a lesser degree onto subscale factors, this indicates that a unidimensional scoring method would be apposite (Reise, Moore, and Haviland 2010).”
Causal feature learning: an overview (2017, neutral): “Psychometric models (see Reise et al. 2010 for a good introduction) have a similar structure to the one presented here (see Fig.”
John Carroll’s Views on Intelligence: Bi-Factor vs. Higher-Order Models (2015, methodology): “Until the recent development of analytic bi-factor rotations [38,60], it made sense to substitute the SLT of a higher-order model for a bi-factor model when conducting an exploratory factor analysis [61].”
The Rediscovery of Bifactor Measurement Models (2012, background): “…resolving important problems in conceptualizing and measuring psychological constructs (Brunner, Nagy, & Wilhelm, 2012; Cai, Yang, & Hansen, 2011; Chen, Hayes, Carver, Laurenceau, & Zhang, 2012; Gustafsson & Aberg-Bengtsson, 2010; Reise et al., 2010; Reise, Morizot, & Hays, 2007; Thomas, 2012); 3.”