Assessing Probabilities of Unique Events: Calibrating Qualitative Likelihood Judgments into a Probability Distribution.
Chinese Business Review, Volume 9 Number 9 (Serial number 87), Sept. 2010, pages 54 - 60.
ABSTRACT: Multifaceted events in an organizational environment usually need to be assigned probabilities as a prerequisite to analytical decision-making. If the decision situation is unique, a lack of relevant historical frequency data may preclude use of traditional probability models such as the normal, binomial etc. In this case, an individual decision maker (DM) or an informed group of persons can input into a procedure as outlined here to determine a probability distribution that leads to expected values of alternative actions or fair values of securities. The individual or group member must decide qualitatively on the extent to which one event is "more likely" than another where both events are ranked adjacent (i.e. closest to each other) in terms of likelihood. Even though the individual or group members may lack experience in orthodox probability assessment, these pairwise "more likely" judgments are not overly demanding for persons familiar with the possible outcomes in the situation under analysis.