Unit And Random Linear Models In Decision Making

Dawes and Corrigan have asserted that linear decision rules using random or unit coefficients "yield predictions that are superior to those of human judges." Their assertion is based on the large correlations between the decisions from random or unit rules and actual decisions. This paper reports an experiment based on the scheduling production problem in which the correlations coefficient is compared with actual costs. In spite of high correlations with the optimal decision, the unit and random rules yielded much higher costs than human judgment.