Decision Analysis current issue

From the Editor...

Keller, L. R. — 2009-09-16

Our first two articles address resource allocation, across risky projects and across budget allocations over time. First, Philip Bromiley demonstrates numerically that the interaction between cumulative prospect theory parameters rules out the ability to make simple general predictions of resource allocation choices in "A Prospect Theory Model of Resource Allocation." Our second article, by Pekka Mild and Ahti Salo, on "Combining a Multiattribute Value Function with an Optimization Model: An Application to Dynamic Resource Allocation for Infrastructure Maintenance," reports a generic model for allocating maintenance budgets over time that was originally developed for the Finnish Road Administration. Our third article, by Jesus Rios and David Rios Insua, develops a method for "Supporting Negotiations over Influence Diagrams," for when there is disagreement about utilities and probabilities. Fourth, Ben Ewing and Erin Baker present their work on the "Development of a Green Building Decision Support Tool: A Collaborative Process." In our final article, "On the Decision to Take a Pitch," J. Eric Bickel analyzes a common decision in baseball, contributing to the area of sports decision analysis.

A Prospect Theory Model of Resource Allocation

Bromiley, P. — 2009-09-16

Many papers in organization theory and strategy use prospect theory, but few derive their hypotheses from prospect theory's formal model. This paper develops a prospect theory model of resource allocation under risk where projects have both positive and negative adjusted payoffs. The model assumes consistent value (rather than profit) maximizing behavior and demonstrates how resources, risk propensity, and reference levels interact to determine allocations to risky projects. The analysis shows that prospect theory's parameters interact in complex ways to influence risk taking, which makes simple predictions difficult. Overall, loss aversion and the reference point dominate the results, with curvature of the value function playing a secondary role and the maximum risk aversion occurring for firms near their reference points, not for firms above their reference points.

Combining a Multiattribute Value Function with an Optimization Model: An Application to Dynamic Resource Allocation for Infrastructure Maintenance

Mild, P., Salo, A. — 2009-09-16

A key decision in infrastructure management is the allocation of resources to maintenance activities that consist of periodic rehabilitation actions and routine day-to-day operations. These activities improve the quality of different assets and operations. They also differ in terms of their objectives, costs, and life-cycle characteristics; yet they all impact the same infrastructure system and compete for resources from the same budget. To support the allocation of resources to these activities, we present a generic resource allocation model that we developed for the Finnish Road Administration (Finnra) by building and interlinking (i) a preference model, which yields the aggregate value of maintenance activities by applying multiattribute value functions to the quality distributions of assets; (ii) a life-cycle model, which captures the deterioration-improvement dynamics associated with the maintenance activities; and (iii) an optimization model, which generates funding recommendations for maximizing the aggregate long-term value of maintenance investments. The optimization results were explored in facilitated workshops where "on-the-fly" computations gave senior managers insights into how the recommendations depended on preferences and budget levels. The case study was awarded for an outstanding achievement in Finnra's research program, and it was also recognized as a Finalist for the Decision Analysis Society Practice Award in 2007.

Supporting Negotiations over Influence Diagrams

Rios, J., Insua, D. R. — 2009-09-16

We deal with issues concerning negotiation support for group decisions over influence diagrams, when the group members disagree about utility and probability assessments. We base our discussion on a modification of the balanced increment solution, which guarantees a final negotiated Pareto optimal alternative. As in standard decision analysis textbooks, we deal first with negotiation tables, then with negotiation trees, and finally with negotiation influence diagrams. We show through an example that a naive application of the balanced increment method at each joint decision node in a dynamic decision-making problem, and, more generally, of any standard negotiation approach guaranteeing Pareto optimality, may lead to an inferior solution. Therefore, our strategy proposes computing first the set of nondominated alternatives followed by negotiating over that set.

Development of a Green Building Decision Support Tool: A Collaborative Process

Ewing, B., Baker, E. — 2009-09-16

In this paper, we discuss a collaborative process for developing a decision tool to support decisions around investment in green energy technologies. Our tool was developed specifically for the Hitchcock Center for the Environment, a local environmental education organization, and the development process began as an undergraduate student service learning project. Building on the student projects, we developed an Excel-based tool that allows users to select various combinations of technologies and instantly see the financial, environmental, and educational impacts of their choice. Given our initial parameters and the preferences of the Hitchcock Center staff, the optimal configuration included installing a biomass heating system and a composting toilet, but avoiding investment in other green technologies, yielding an annualized preference-adjusted cost of $5,252.58. Sensitivity analysis indicated that the optimal choice was not sensitive to environmental valuations, and only slightly sensitive to educational values. All participants in the process found the concept and practice of value elicitation to be useful and illuminating.

On the Decision to Take a Pitch

Bickel, J. E. — 2009-09-16

Baseball is a highly strategic game, with decisions being made almost continuously. In this paper, we analyze the decision to have the batter take a pitch, which means that he does not swing at the pitch under any circumstances—even if it is easily hittable. Why would a batter do this? Using decision-theoretic reasoning, we determine under what circumstances such a decision is good. We find that in some cases, taking pitches deterministically dominates not taking.

About the Authors

2009-09-16

No abstract available.

INFORMS MEETING CALENDAR

2009-09-16

No abstract available.