Using Beta Coefficients to Impute Missing Correlation Coefficients in Meta-Analytic Research: Reasons for Caution
Journal of Applied Psychology, Forthcoming
50 Pages Posted: 26 Nov 2017 Last revised: 9 Jan 2018
Date Written: November 21, 2017
Meta-analysis has become a well-accepted method for synthesizing empirical research about a given phenomenon. Many meta-analyses focus on synthesizing correlations across primary studies, but some primary studies do not report correlations. Peterson and Brown (2005) suggested that researchers could use standardized regression weights (i.e., beta coefficients) to impute missing correlations. Indeed, their beta estimation procedures (BEPs) have been used in meta-analyses in a wide variety of fields. In this study, we evaluated the accuracy of BEPs in meta-analysis. We first examined how use of BEPs might affect results from a published meta-analysis. We then developed a series of Monte Carlo simulations that systematically compared the use of existing correlations (that were not missing) to data sets that incorporated BEPs (that impute missing correlations from corresponding beta coefficients). These simulations estimated (mean population correlation) and SDρ (true standard deviation) across a variety of meta-analytic conditions. Results from both the existing meta-analysis and the Monte Carlo simulations revealed that BEPs were associated with potentially large biases when estimating and even larger biases when estimating SDρ. Using only existing correlations often substantially outperformed use of BEPs and virtually never performed worse than BEPs. Overall, we urge a return to the standard practice of using only existing correlations in meta-analysis.
Keywords: beta estimation procedures, meta-analysis, missing data
Suggested Citation: Suggested Citation