Development and psychometric evaluation of the E-sports Attitude Scale

Abstract

This study aimed to develop and conduct a comprehensive psychometric evaluation of a scale designed to measure university students' attitudes toward esports. The research was carried out using a correlational research design. Two independent samples selected using maximum variation sampling were utilized: 797 students participated in the exploratory factor analysis (EFA), while 794 students were included in the confirmatory factor analysis (CFA). The EFA results revealed a four-factor structure-socialization, individualization, career, and risks-explaining 64% of the total variance. The CFA supported this structure with excellent model fit indices (CFI = .99, TLI = .98, RMSEA = .05, SRMR = .06). Reliability analyses demonstrated high internal consistency, with Cronbach's alpha ranging from .89 to .93, McDonald's omega between .90 and .94, and stratified alpha (.94) as well as Revelle's omega (.97) for the total scale. Furthermore, measurement invariance across gender was examined and supported, indicating that the scale functions equivalently for male and female respondents. Additionally, Differential Item Functioning (DIF) analysis based on ordinal logistic regression revealed no significant gender-related item bias, reinforcing item-level fairness. These findings provide strong evidence for the validity, reliability, and fairness of the E-sports Attitude Scale, confirming its suitability for measuring attitudes toward e-sports in higher education contexts.