Correcting the Effect Size of d for Range Restriction and Unreliability

Abstract

Pearson product moment correlations are often corrected for statistical artifacts such as range restriction and unreliability. Formulas have long existed to make such corrections. However, other effect size estimates are rarely corrected for these artifacts, in spite of the fact that there is an established mathematical link between the correlation and some effect size estimates. Correlations and other effect sizes are therefore vulnerable to the same artifacts. The authors take a common effect size estimate, the standardized mean difference between two groups, and derive (and reaffirm in one instance) correction formulas suitable for use with this statistic. It is demonstrated how these formulas might substantially increase the precision of estimates and decisions made within organizational research and practice, whenever correction factors can be appropriately estimated.