Gender bias in the measurement of peer victimization: an application of item response theory.

There continues to be great debate regarding the conceptualization and measurement of peer victimization, particularly with respect to gender differences in children's victimization experiences. We employed traditional and modern psychometric methods (e.g., item response theory) to evaluate a 10-item youth-report measure of peer victimization (e.g., threatening, spreading rumors/lies, and cyberbullying) among 17,198 students in Grades 6-12. A two-factor model that differentiated between direct and indirect victimization subtypes best characterized students' experiences and substantially reduced the potential for gender-based measurement bias. Implications for the gender-sensitive assessment of peer victimization are discussed.