Variance Structure of Academic Achievement

A major, multi-year initiative directed by Co-PI Hedges was designed to help investigators determine whether an intervention has significant effects on learning and instruction. The product of this effort was a multi-volume compilation of intraclass correlation values of academic achievement and related covariate effects that can be used for planning group-randomized experiments in education. Specifically, this Variance Almanac allows researchers to compute the statistical power and samples sizes needed to achieve generalizable results. Early findings from this work were presented by Hedges in a keynote address to the 2006 Annual IERI PI meeting, “Variance structure of academic achievement in America: Reference values for planning evaluation studies.” Related publications include:

• Hedges, L.V., & Hedberg, E.C. (2007a). Intraclass correlation values for planning group-randomized trials in education. Educational Evaluation and Policy Analysis, 29(1): 60-87.

• Hedges, L.V., & Hedberg, E.C. (2007b). Intraclass correlation values for planning group-randomized experiments in rural education. Journal of Research in Rural Education, 22(3): 1-15.