Aggregation and the estimated effects of school resources

Abstract

This paper helps reconcile the contradictory findings about school resources and school effectiveness by developing the implications of data aggregation. With model misspecification, the theoretical impact of aggregation is generally ambiguous. When important state differences in school policy are omitted, however, aggregation implies clear upward bias of estimated school resource effects. Review of past studies and new empirical analysis provide strong evidence that aggregation inflates the coefficients on school resources. The pattern of results is also inconsistent with an errors-in-variables explanation. These results provide further support to the view that additional expenditures alone are unlikely to improve student outcomes.