Detecting Item BIAS in Affective Scales

Abstract

The purpose of the study was to demonstrate the use of confirmatory factor analysis to investigate the existence of item bias in an affective scale measuring self-concept. The data were collected from three ethnic groups (Black, Hispanic, and White) in grade eight (N = 1264). The factor structure and item uniqueness were simultaneously compared across ethnic groups by using the LISREL program. A differential response pattern found across the three groups indicated potential bias in score interpretation. The study illustrated that structural analysis may be a useful methodology in the investigation of item bias in affective scales.