Incorporating risk into selection utility: Two models for sensitivity analysis and risk simulation

Abstract

This study offers two techniques for assessing the impact of uncertainty in inputs such as the number of selectees and the selection ratio on selection utility estimates. These models, which express utility as an expected distribution of net present values, extend recent advances in finance theory to utility estimation. Sensitivity analysis and a risk simulation were run using actual data collected for the clerical/administrative trade group in the Canadian military. Although the overall level of utility resulting from use of the existing ability test composite was very high, the results demonstrated that considerable risk was associated with the selection investment. One input (i.e., number of selectees or N_s) was identified as the major contributor to risk in the utility analysis. Further refinement of the N_s input was recommended. Sensitivity analysis and risk simulation were recommended as valuable tools for more adequately representing the benefits achievable from personnel programs Such as selection.