DIRECT ESTIMATES OF SDY AND THE IMPLICATIONS FOR UTILITY ANALYSIS

Utility analysis suggests that human resources policies can have an economically significant im-pact on business organizations. Confidence in such conclusions, however, requires an accurate estimate of SD(y). This article provides a validity check on prevailing subjective methods of SD(y) estimation by directly estimating SD(y) from unique field data. Using both simulated and field data, we first illustrate the range of potential bias associated with predictor unreliability in regression analysis and show how to calculate corrected values. We then discuss the methodological problems of directly estimating SD(y) with organizational data and provide a range of estimates for SD(y). Our direct estimation of SD(y) yielded values ranging from 74% to 100% of mean salary, which are considerably greater than conventional subjective judgments.