Psychometrics

Item Response Theory Modelling of the Trait Emotional Intelligence Questionnaire-Short Form: Item Streamlining, Differential Item Functioning, and Validity in a Swedish Multicenter Cross-Sectional Study

We applied IRT to evaluate and refine the 30-item Trait Emotional Intelligence Questionnaire-Short Form (TEIQue-SF) in a Swedish sample of 845 healthcare and social work students. IRT identified underperforming items, yielding a refined 12-item version that effectively captures trait EI with good reliability and strong convergent validity.

Validation of Subjective Well-Being Measures Using Item Response Theory

We applied IRT to validate three subjective well-being scales in a sample of 1,000 participants. All scales showed high item discrimination values and varied difficulty parameters. Negative affect and extreme latent scores were less reliably measured, while cognitive and social well-being components were covered equally well.

IRT Analyses of the Swedish Dark Triad Dirty Dozen

We applied Item Response Theory to the Swedish Dark Triad Dirty Dozen (N = 570). Contrary to findings on the English version, narcissism provided most information, followed by psychopathy, then Machiavellianism. Psychopathy items required higher latent trait levels for endorsement, possibly reflecting Swedish cultural conditions.

Testing Construct Independence in the Short Dark Triad Using Item Response Theory

We analyzed the Short Dark Triad (SD3) in a large sample (N = 1,983) using Item Response Theory. Machiavellianism items showed lower endorsement thresholds than psychopathy items. IRT model fit testing showed that Machiavellianism and narcissism could not be modelled together, while Machiavellianism-psychopathy and narcissism-psychopathy combinations yielded acceptable fit.

Revisiting the Structure of the Short Dark Triad

We investigated the SD3’s factor structure in three independent samples using exploratory and confirmatory factor analyses. Machiavellianism and psychopathy items showed large general factor loadings while narcissism loaded more on a specific factor. A bifactor model fit best, and we recommend using the SD3 composite score rather than subscale scores.

The (Mis)measurement of the Dark Triad Dirty Dozen: Exploitation at the Core of the Scale

We replicated the factor structure and item response properties of the Dark Triad Dirty Dozen (DD) in a sample of 3,698. Results confirmed a bi-factor model, but suggest the DD is best understood as a combined Machiavellianism-psychopathy factor, with its core captured by a single exploitativeness item.