A known group analysis validity study of the Vanderbilt Assessment of Leadership in Education in US elementary and secondary schools

Abstract

The Vanderbilt Assessment of Leadership in Education (VAL-ED) provides educators with a tool for principal evaluation based on principal, teacher, and supervisor reports of principals’ learning-centered leadership. In this study, we conduct a known group analysis as part of a larger argument for the validity of the VAL-ED in US elementary and secondary schools. We asked superintendents to select the principals in their district who they believe in performance of their duties are in the top 20 % and the bottom 20 %. We ask how accurately VAL-ED scores can identify membership of the two known groups. Using a discriminant analysis, the VAL-ED places principals in the superintendent groups, on average, 70 % of the time for both elementary and secondary schools. Placement accuracy is greater for the top group than the bottom group.