Assessment of probability distributions for continuous random variables: A comparison of the bisection and fixed value methods

Comparisons between two methods of assessing an individual's probability distribution for a continuous variable are provided. These two methods are bisection assessment and direct assessment. The subjects in the study were scientists and engineers participating in a formal probability elicitation process directed toward assessing the risks from nuclear power generating stations. The subjects were trained in probability elicitation and then asked to give probability distributions for almanac values as part of the debiasing training. The results show little difference between the direct and the bisection methods. Slightly better performance, as measured through the calibration of the distributions, was obtained using the bisection method. This result is contrary to strong results obtained in previous studies. The difference in conclusions can be explained by differences in procedures for obtaining end points of the distributions. Also obtained was evidence showing the use of logarithmic scales in place of linear scales may improve the calibration of assessed distributions.