Files in this item



application/pdfHUPMAN-DISSERTATION-2015.pdf (3MB)
(no description provided)PDF


Title:Theoretical and experimental examinations of target-based decision making
Author(s):Hupman, Andrea C.
Director of Research:Abbas, Ali E.
Doctoral Committee Chair(s):Beck, Carolyn
Doctoral Committee Member(s):Price, Raymond; Michael, Steven
Department / Program:Industrial&Enterprise Sys Eng
Discipline:Systems & Entrepreneurial Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):decision analysis
target-based decision making
Abstract:Target based decision making occurs when a decision maker wishes to maximize the probability of attaining some output or performance level. The target may be set externally, for example, by an employer as part of an incentive system. Or, the target may simply be based on a decision maker’s individual goals and understanding of implicit expectations. Questions arise concerning the effects of these decisions on the performance of an organization. Further, if these decisions affect organizational value, how well can these decisions be characterized and predicted? This research explores these questions—and others—using both theoretical and experimental means. A value gap model is developed that facilitates simulation based insights to target optimality. The effect of a target is characterized in terms of a value gap that is defined as the difference in value between what was selected based on a target and what the organization would have preferred. A copula based method is used to simulate future decision situations and the expected value gap is calculated as a function of model parameters. Several trends in target optimality are observed that are robust to changes in the probability distributions over future decision alternatives. Specifically, the optimal target (i) decreases as the organization’s risk aversion increases, (ii) increases as the number of available alternatives increase, and (iii) the presence of an efficient frontier of decision alternatives reduces the consequences of setting targets higher than optimal. A behavioral experiment is conducted to compare target-based decision making to decisions in the absence of a target. The results show that while target based decision making can be well predicted based on the properties of the decision alternatives alone. Decisions in the absence of a target, however, cannot be predicted based on the alternatives alone. Information about individualized differences in risk preferences is required to identify trends in the decision making behavior. These results have strong implications for decisions about whether or not to used target based incentives within an organization. The research concludes with an application to engineering systems and a discussion of additional questions raised by the research that point to directions for new research.
Issue Date:2015-04-20
Rights Information:Copyright 2015 Andrea C. Hupman
Date Available in IDEALS:2015-07-22
Date Deposited:May 2015

This item appears in the following Collection(s)

Item Statistics