The Effects of Class Size: An Examination of Rival Hypotheses

Abstract

There has recently been a great deal of interest in the use of meta-analysis to integrate research findings. Glass and Smith used meta-analytic techniques to describe the relationship between class size and academic achievement or classroom processes. The statistical methods used by Glass and Smith are open to criticism on several grounds. The present paper reports the results of reanalyses using statistical methods that can be rigorously justified. The statistical methods used herein can be shown to have certain optimal properties for the analysis of effect size data, and therefore the results of analyses based on these methods are generally preferable. The results of our analyses suggest that the use of suboptimal statistical methods did not greatly affect the results of the meta-analysis by Glass and Smith.