Innovate Collaborate Grow

 
 
Faculty & Research

Research Colloquium 2013-2014

Join us for the final Distinguished Speaker Series event of the academic year on Wednesday, April 30, 2014 featuring Bernie Clark, Executive Vice President, Advisor Services at Charles Schwab & Co., Inc. This is truly an event that can't be missed! For more information and to reserve your seat today, please visit the DSS event page.

Operations & Decision Technologies

 

Professor Carlton Scott

Title: "Approximate and Exact Formulas for the (Q r) Inventory Model" 

Co-author: Zvi Drezner

Accepted at: Journal of Industrial and Management Optimization

January 2014

 

In this paper, new results are derived for the (Q, r) stochastic inventory model.  We derive approximate formulas for the particular case of an exponential demand distribution.  The approximate solution is within 0.29% of the optimal value.  We also derive simple formulas for a Poisson demand distribution.  The original expression consists of double summation.  We simplify the formula and are able to calculate the exact value of the objective function in O(1) time with no need for any summations.

 


   

Professor Robin Keller

Title: "An Empirical Study of the Toxic Capsule Crisis in China: Risk Perceptions and Behavioral Responses" 

Co-authors: Tianjun Feng (Ph.D alumni), Ping Wu and Yifan Xu

Accepted at: Risk Analysis

October 2013

 

The outbreak of the toxic capsule crisis during April 2012 aroused widespread public concern about the risk of chromium-contaminated capsules and drug safety in China.  In this paper, we develop a conceptual model to investigate risk perceptions of the pharmaceutical drug capsules and behavioral responses to the toxic capsule crisis and the relationship between associated factors and these two variables.  An online survey was conducted to test the model, including questions on the measures of perceived efficacy of the countermeasures, trust in the State FDA (Food and Drug Administration), trust in the pharmaceutical companies, trust in the pharmaceutical capsule producers, risk perception, concern, need for information, information seeking, and risk avoidance.  In general, participants reported higher levels of risk perception, concern, and risk avoidance, and lower levels of trust in the three different stakeholders.  The results from the structural equation modeling procedure suggest that perceived efficacy of the countermeasures is a predictor of each of the three trust variables; however, only trust in the State FDA has a dampening impact on risk perception.  Both risk perception and information seeking are significant determinants of risk avoidance.  Risk perception is also positively related to concern.  Information seeking is positively related to both concern and need for information.  The theoretical and policy implications are also discussed.
 

Professor Robin Keller

Title: "Decision Analysis with Geographically Varying Outcomes: Preference Models and Illustrative Applicaitons" 

Co-authors: Craig W. Kirkwood and Jay Simon (Ph.D alumni)

Accepted at: Operations Research

October 2013

 

This paper presents decision analysis methodology for decisions based on data from geographic information systems.  The consequences of a decision alternative are modeled as distributions of outcomes across a geographic region.  We discuss conditions which may conform with the decision maker’s preferences over a specified set of alternatives; then we present specific forms for value or utility functions that are implied by these conditions.  Decisions in which there is certainty about the consequences resulting from each alternative are considered first; then probabilistic uncertainty about the consequences is included as an extension.  The methodology is applied to two hypothetical urban planning decisions involving water use and temperature reduction in regional urban development, and fire coverage across a city.  These examples illustrate the applicability of the approach and the insights that can be gained from using it.

 

Professor Carlton Scott

Title: "Location of a Distribution Center for a Perishable Product" 

Co-author: Zvi Drezner

Accepted at: Mathematical Methods of Operations Research

October 2013

 

A model that combines an inventory and location decision is presented, analyzed and solved. In particular, we consider a single distribution center location that serves a finite number of sales outlets for a perishable product. The total cost to be minimized, consists of the transportation costs from the distribution center to the sales outlets as well as the inventory related costs at the sales outlets. The location of the distribution center affects the inventory policy. Very efficient solution approaches for the location problem in a planar environment are developed. Computational experiments demonstrate the efficiency of the proposed solution approaches.

 


   

Professor Shuya Yin

Title: "Returns Policies between Channel Partners for Durable Products" 

Co-authors: Mehmet Gumus and Saibal Ray

Accepted at: Marketing Science

March 2013

 

Many durable products with relatively short selling seasons have been using returns policies between manufacturers and retailers as the contractual protocol for some time. Recently, these sectors have witnessed the growing popularity of peer-to-peer (P2P) web-based used goods markets as important transaction channels between buyers and sellers. Given that these two issues are critically linked from both supply and demand perspectives, in this paper, we study what role consumer valuation of used products plays in shaping a manufacturer's incentive to offer a returns policy option to a retailer, when used goods might be devalued compared to new ones due to physical deterioration (or obsolescence). We do so through a two-period dyadic channel framework where the retailer faces uncertain demand for a durable product from a renewable set of customers, who are impatient but forward-looking. The manufacturer, on the other hand, needs to decide whether or not to offer a returns contract to the retailer. We first characterize the necessary and sufficient condition under which a returns contract is the equilibrium strategy as well as the corresponding channel decisions. Further analysis of this condition reveals that higher consumer valuation of used products increases the likelihood of a returns contract to be the equilibrium strategy. This result seems to be robust except when the potential demands for the two periods are quite deterministic and uncorrelated. However, it contradicts the burgeoning managerial trend to replace returns contracts with price-only ones in sectors where used goods are valued relatively highly by the consumers. We also discuss how used goods markets affect the equilibrium channel decisions as well as how demand uncertainty and logistics costs associated with returns influence the equilibrium contracting strategy.

 

Professor Shuya Yin

Title: "ATM Pricing and Location Games in the Banking Industry" 

Co-authors: Reynold Byers and Xiaona Zheng

Accepted at: Asia-Pacific Journal of Operational Research

March 2013

 

This paper studies a competitive Hotelling-style market with two symmetric banks that decide the pricing and location of their automated teller machines (ATMs). Two different systems are considered: an unregulated model wherein banks are allowed to set surcharges, and a regulated model in which surcharges are banned. We derive equilibrium outcomes and compare them in the two systems, and find that banks always maintain a certain distance between ATMs. That distance is larger, indeed maximized, under the regulatory scheme. We also show that, surprisingly, banks would actually always perform better in the regulated model, while consumers may be worse off.

 


  

Professor Robin Keller

Title: "A Further Exploration of the Uncertainty Effect" 

Co-authors: Yitong Want and Tianjun Feng (Ph.D alumni)

Accepted at: Journal of Risk and Uncertainty

February 2013

 

Individual valuation of a binary lottery at values less than the lottery’s worst outcome has been designated as the “uncertainty effect”.  Our paper aims to explore the boundary conditions of the uncertainty effect by investigating a plausible underlying process and proposing two possible methods.  First, we examine how providing an exogenous evaluation opportunity prior to judging the value of the lottery affects individuals’ judgments, and find that first valuing the worst outcome and then the lottery eliminates the uncertainty effect.  Second, we explore if introducing additional cognitive load dampens how far decision makers correct their initial evaluations, and find that additional cognitive load is able to eliminate the uncertainty effect.

 

 


 

Professor Carlton Scott

Title: "One Tailed Tests of Means of Multivariate Normal Distributions Derived by Generalized Geometric Programming" 

Co-author: T. R. Jefferson

Accepted at: Pacific Journal of Optimization

June 2012

 

This paper studies multivariate one-tailed tests of the means, which occur in many application areas of statistics.  The statistical distribution of the single-sided statistic is found using the union-intersection principle of S.N. Roy to formulate the estimation problem and generalized geometric programming to analyze and solve it.  Generalized geometric programming is key to the solution as it converts the primal problem into a dual problem, which is effectively zero degree of difficulty and thus relatively easy to solve.  The generalized t-statistic (GT) is developed.   is a generalization of the Hotelling  statistic.  This is based on a generalized F statistic, which can be found by solving an equation. Statistical tables are provided.  The statistic is used to perform an hypothesis test on senility using the Wechsler Adult Intelligence Scale

 

 


 

 

Professor John Turner
Title: “A Large U.S. Retailer Selects Transportation Carriers Under Diesel Price Uncertainty”
Co-authors: Ben Peterson, Soo-Haeng Cho, Sunder Kekre, and Alan Scheller-Wolf
Accepted at: Interfaces

September 2011
 
A large U.S. retailer which procures transportation services from third-party carriers experienced an unexpected jump in fuel surcharges as the price of diesel skyrocketed in the summer of 2008. As a result, the retailer sought to limit its future exposure to diesel price risk. We collaborated with the retailer to create a Lane Assignment Optimizer (LAO) which incorporates diesel price risk when selecting carriers for its transportation lanes. The LAO tool has significantly improved the retailer's capability to evaluate the tradeoff between the two crucial components of a lane's per-shipment cost: base price and risk-adjusted fuel surcharge. As a result, the retailer can now select cost-effective carriers for its lanes taking into account diesel price risk, negotiate fuel surcharge limits to share diesel price risk with its carriers, and better align the fuel surcharges it pays with the true cost of diesel. We estimate that the more favorable contract terms the retailer negotiated for 2009-2011 translate to nearly $5 million in potential savings for years with unexpected diesel price hikes like 2008.

 


 

Professor John Turner
Title: “The Planning of Guaranteed Targeted Display Advertising”
Co-authors:
Accepted at: Operations Research

May 2011

As targeted advertising becomes prevalent in a wide variety of media vehicles, planning models become increasingly important to ad networks that need to match ads to appropriate audience segments, provide a high quality of service (meet advertisers' goals), and ensure ad serving opportunities are not wasted. We define Guaranteed Targeted Display Advertising (GTDA) as a class of media vehicles that include webpage banner ads, video games, electronic outdoor billboards, and the next generation of digital TV, and formulate the GTDA planning problem as a transportation problem with quadratic objective. By modeling audience uncertainty, forecast errors, and the ad server's execution of the plan, we derive sufficient conditions that state when our quadratic objective is a good surrogate for several ad delivery performance metrics. Moreover, our quadratic objective allows us to construct duality-based bounds for evaluating aggregations of the audience space, leading to two efficient algorithms for solving large problems: the first intelligently refines the audience space into successively smaller blocks, and the second uses scaling to find a feasible solution given a fixed audience space partition. Near-optimal schedules can often be produced despite significant aggregation.

 


 

Professor Robin Keller
Title: “Making probability judgments of future product failures: The role of mental unpacking”
Co-authors: Dipayan Biswas (PhD Alumnus) and Bidisha Burman
Accepted at: Journal of Consumer Psychology

April 2011
 
When consumers mentally unpack (i.e., imagine) the reasons for product failure, their probability judgments of future product failures are higher than when no mental unpacking is undertaken. However, increasing the level of mental unpacking does not lead to monotonically increasing effects on probability judgments but results in inverted U-shaped relationships. Using a two-factor structure, we propose that when consumers undertake mental unpacking, there will be two conflicting processes; while imagining causes for an event will lead to greater perceived probability, the greater difficulty in generating reasons for an event will lead to lower perceived probability.

 


 

PhD Student James M. Leonhardt and Professors L. Robin Keller and Cornelia Pechmann
Title: “Avoiding the Risk of Responsibility by Seeking Uncertainty: Responsibility Aversion and Preference for Indirect Agency When Choosing for Others”
Co-authors: 
Accepted at: Journal of Consumer Psychology 

February 2011

Uncertainty-seeking behavior is currently understood as the result of loss aversion which motivates a preference for the possibility to avoid or lessen an otherwise sure loss. However, when choosing among negative options on behalf of others, we offer responsibility aversion as another possible motive for uncertainty-seeking behavior. Within our conceptual model, responsibility aversion is defined as the preference to minimize one’s causal role in outcome generation. Compared to certain options, uncertain options lessen the decision maker’s causal role in outcome generation because the outcomes are partially determined by chance. The presence of chance increases indirect agency on behalf of the decision maker and lessens his or her perceived risk of responsibility. The results of five studies support a responsibility aversion motivation behind uncertainty-seeking behavior.

  


  

Professor Shuya Yin
Title: “The Equivalence of Uniform and Shapley Value-Based Allocations in a Specific Game”
Co-authors: Rachel R. Chen
Accepted at: Operations Research Letters

November 2010

This paper concerns the possible equivalence of the Shapley value and other allocations in specific games. For a group buying game with a linear quantity discount schedule, the simple, commonly-used uniform allocation results in the same cost allocation to buyers as the Shapley value-based allocation. In this paper, we explore whether the Shapley axioms can be used to make such connections. We show that an allocation that satisfies the additivity axiom for all games, and the symmetry, null player and efficiency axioms for a specific game does not imply the equivalence of this allocation with the Shapley value in this game. We also characterize the functions that result in the equivalence of the uniform allocation and the Shapley value among the class of polynomial total cost functions.

  


 

Professor Robin Keller and PhD Student Yitong Wang
Title: “Product Quality Risk Perceptions and Decisions: Contaminated Pet Food and Lead-Painted Toys”
Co-authors: doctoral alumni Tianjun Feng and Liangyan Wang
Accepted at: Risk Analysis

June 2010

In the context of the recent recalls of contaminated pet food and lead-painted toys in the United States, we examine patterns of risk perceptions and decisions when facing consumer product-caused quality risks.  Two approaches were used to explore risk perceptions of the product recalls.  In the first approach, we elicited judged probabilities and found that people appear to have greatly overestimated the actual risks for both product scenarios.  In the second approach, we applied the psychometric paradigm to examine risk perception dimensions concerning these two specific products through factor analysis.  There was a similar risk perception pattern for both products: they are seen as unknown risks and are relatively not dread risks.  This pattern was also similar to what prior research found for lead paint.  Further, we studied people’s potential actions to deal with the recalls of these two products.  Several factors were found to be significant predictors of respondents’ cautious actions for both product scenarios.  Policy considerations regarding product quality risks are discussed.  For example, risk communicators could reframe information messages to prompt people to consider total risks packed together from different causes, even when the risk message has been initiated due to a specific recall event.

  


 

Professor Rick So and PhD Student Wenting Pan
Title: “Optimal Product Pricing and Component Production Quantities for an Assembly System Under Supply Uncertainty”
Co-authors:
Accepted at: Operations Research

April 2010

We consider an assemble-to-order system where one of the components faces uncertainty in the supply process in which the actual available quantity is equal to some random fraction of the production quantity.  Demand is assumed to be price-dependent.  We analyze how the supply uncertainty of one component affects the product pricing and production quantities of all the components under the assembly structure.  We show that it is profitable for the firm to assemble the product only if the product price exceeds a certain threshold. This price threshold increases as the unit cost of each component or the degree of variability of the supply reliability distribution increases, but is independent of the underlying demand function and demand distribution.  Also, the optimal product price decreases as supply uncertainty decreases.  We further show that under deterministic demand, the components can be managed independently such that the production quantity or unit cost of the component with supply uncertainty does not affect the optimal production quantity of the other components as long as it is profitable to assemble the product.  However, when demand is stochastic, the optimal production quantity of each component depends on the supply reliability distribution as well as the unit costs of the other components.  For a fixed product price, the optimal production quantities of the components are smaller when the unit product price is low, and are higher when the unit product price is high as compared to the case with no supply uncertainty.

  


 

Professor Robin Keller
Title: “Decision Making in the Newsvendor Problem: A Cross-national Laboratory Study”
Co-authors: Tianjun Feng (doctoral alumnus) and Xiaona Zheng
Accepted at: Omega, The International Journal of Management Science

March 2010

In this paper, we conduct a laboratory experiment using the classic newsvendor problem to examine cross-national differences in inventory ordering patterns between Chinese and American decision makers based on a theoretical examination of the role of the Doctrine of the Mean in Chinese decision making.  Drawing on the theory of context-dependent preferences (specifically extremeness aversion), we also revisit the flat-maximum hypothesis of Bolton and Katok (2008), i.e., “thinning the set of order options leads to newsvendor decisions that achieve a higher proportion of maximum expected profit.”  The results show that the “pull-to-center” effect is more prominent for Chinese than Americans, i.e., average order quantities of Chinese subjects are closer to the anchor of mean demand than those of American subjects.  Furthermore, we find that thinning the set of order options such that the optimal order quantity is a middle option, not an extreme option in the choice set, leads to better performance in newsvendor decisions, which complements the flat-maximum hypothesis.

  


 

Professors Carlton Scott and Zvi Drezner
Title: “Optimizing the Location of a Production Firm”
Accepted at: Networks and Spatial Economics

January 2010

A facility needs to be located in the plane to sell goods to a set of demand points. The cost for producing an item and the actual transportation cost per unit distance are given. The planner needs to determine the best location for the facility, the price charged at the source (mill price) and the transportation rate per unit distance to be charged to customers. Demand by customers is elastic and assumed declining linearly with the total charge. For each customer two parameters are given: the demand at charge zero and the decline of demand per unit charge. The objective is to find a location for the facility in the plane, the mill price charged to customers and the unit transportation rate charged to customers such that the company’s profit is maximized. The problem is formulated and an algorithm that finds the optimal solution is designed and tested on randomly generated problems.

  


 

Professor Shuya Yin
Title: “Alliance Formation among Perfectly Complementary Suppliers in a Price-Sensitive Assembly System”
Co-authors:
Accepted at: Manufacturing and Service Operations Management (MSOM)

November 2009

Independent parties who produce perfectly complementary components may form alliances (or coalitions or groups) to better coordinate their pricing decisions when they sell their products to downstream buyers. This paper studies how market demand conditions (i.e., the form of the demand function, demand uncertainty, and price-sensitive demand) drive coalition formation among complementary suppliers. In the model with deterministic demand, we show that for an exponential or iso-elastic demand function, suppliers always prefer selling in groups; while for a linear-power demand function, suppliers may all choose to sell independently in equilibrium. These results are interpreted through the pass-through rate associated with the demand function. In the model with uncertain demand, we show that, in general, the introduction of a multiplicative stochastic element into demand has an insignificant impact on stable coalitions, and that an endogenous retail price (i.e., demand is price-sensitive) increases suppliers' incentives to form alliances relative to the case with a fixed retail price. We also consider the impact of various other factors on stable outcomes in equilibrium, e.g., sequential decision making by coalitions of different sizes, the cost effect due to alliance formation (either cost savings or additional costs), and a system without an assembler.

  


 

Professor Shuya Yin
Title: “Durable Products with Multiple Used Goods Markets: Product Upgrade and Retail Pricing Implications”
Co-authors: Saibal Ray, Haresh Gurnani, Animesh Animesh
Accepted at: Marketing Science

October 2009

Used goods markets are nowadays important transaction channels for durable products. For some durable products, such markets first appeared when retailers started buying back used products from “old” customers and selling them to new ones for a profit (retail used goods market). The growth of electronic peer-to-peer (P2P) markets opened up a second, frictionless used goods channel where new customers can buy used products directly from “old” ones (P2P used goods market). Both these markets compete with the original primary market whereby retailers sell unused products procured from the manufacturer. This paper focuses on understanding the role that the sequential emergence of the above two used goods markets plays in shaping the product upgrade strategy of the manufacturer and the pricing strategy of the retailer. We do so in the context of a decentralized, dyadic channel dealing with a renewable set of consumers. Our analysis establishes that frequent product upgrades and rising retail prices in durable product sectors of our interest are due to the emergence of the P2P used goods market and how it interacts with the retail used goods source in altering the relative powers of the channel partners. Moreover, contrary to popular belief, we show that the initial introduction of the retail used goods channel actually discourages introduction of new versions and restrains the rise in retail prices. We also comment on how the two used goods markets affect the profits of the channel partners. We then provide empirical support for our theoretical result regarding product upgrades using data from college textbook industry, a durable product which fits our model setup.

 


 

Professor Carlton H. Scott
Title: “Location of a Facility Minimizing Nuisance to or from a Planar Network”  
Accepted at: Computers and Operations Research
Co-authors: Z. Drezner and T. Drezner
December 2008
   
In this paper we investigate the location of a facility anywhere inside a planar network. Two equivalent problems are analyzed. In one problem it is assumed that the links of the network create a nuisance or hazard and the objective is to locate a facility where the total nuisance is minimized. An equivalent problem is locating an obnoxious facility where the total nuisance generated by the facility and inflicted on the links of the network is minimized. Exact and approximate solution methods for its solution are proposed and tested on a set of planar networks with up to 40,000 links yielding good results.

  


 

Professor Carlton H. Scott
Title: “Geometric Programming Models for Multiple Resource Allocation in Project Management”            
Accepted at: International Journal of Operations and Quantitative Management.
Co-authors: T.R. Jefferson and S. Jorjani
December 2008
 
A convenient way of representing precedence relationships in a multi-activity project is with a network diagram where each node represents an independent activity of certain duration and arcs denote the direction of time. An activity time can generally be reduced by the addition of resources to an activity.  In this paper, we assume that the activity duration is a function of multiple resources and that a finite amount of each resource is available for distribution over the entire project. The objective is to allocate multiple resources to each activity so that the critical path is as short as possible. We give two geometric programming formulations of this problem. The first is a path formulation to which we derive geometric programming dual. The second is a more traditional node-arc formulation which results in a different geometric program. A numerical example and conclusions are given.

  


 

Professor Carlton H. Scott
Title: “Location of a Facility Minimizing Nuisance to or from a Planar Network”  
Accepted at: Computers and Operations Research
Co-authors: Z. Drezner and T. Drezner
December 2008
   
In this paper we investigate the location of a facility anywhere inside a planar network. Two equivalent problems are analyzed. In one problem it is assumed that the links of the network create a nuisance or hazard and the objective is to locate a facility where the total nuisance is minimized. An equivalent problem is locating an obnoxious facility where the total nuisance generated by the facility and inflicted on the links of the network is minimized. Exact and approximate solution methods for its solution are proposed and tested on a set of planar networks with up to 40,000 links yielding good results.

 

  


 

Professor L. Robin Keller
Title: “Modeling Multi-Objective Multi-Stakeholder Decisions: A Case-Exercise Approach”
Accepted at: INFORMS Transactions on Education           
Co-author(s): Tianjun Feng (doctoral alumnus), Xiaona Zheng (former doctoral student)
November 2008
 
The multi-objective multi-stakeholder decision modeling methodology is an effective way to describe and aid context-rich idiosyncratic organizational decision making situations that traditional single attribute decision methodologies can not tackle. The purpose of this paper is to demonstrate how to teach students this methodology as a decision making tool to analyze real-life decision problems using two business decisions as examples (the StarKist decision and the Home Depot case). In particular, we discuss the specific skills students are expected to learn, such as dynamic sensitivity analysis, and typical student questions and errors during case discussion. This methodology has been taught successfully in decision analysis courses both for MBA (including full-time MBA students, business and health care executive MBA students) and undergraduate students.

  


 

Professor L. Robin Keller
Title:  “Assessing Stakeholder Evaluation Concerns:  An Application to the Central Arizona Water Resources System”    
Accepted at: Systems Engineering     
Co-author(s): Craig W. Kirkwood (Arizona State University), and Nancy S. Jones, (Baltimore Metropolitan Council)
November 2008
 
We present an approach for efficiently assessing stakeholder evaluation concerns in the first stage of problem structuring for decisions involving complex systems. We used a web survey to assess the appropriateness of a set of evaluation concerns for evaluating Central Arizona water resources system policies and to gather information on stakeholder priorities. The resulting set of concerns brings a “decision focus” to the modeling efforts of the NSF-funded Decision Center for a Desert City at Arizona State University.  This problem structuring approach, the set of evaluation concerns, and the analysis of variations among stakeholder group priorities can serve as a starting point for other similar policy settings.

 

  


 

Professor Rick So
Title: “The Effect of Supply Reliability in a Retail Setting with Joint Marketing and Inventory Decisions”       
Accepted at: Manufacturing and Service Operations Management
Co-author(s):  Shaoxuan Liu (doctoral alumnus) (Shanghai Jiao Tong University) and Fuqiang Zhang (Washington University)
November 2008 
 
Our paper studies the impact of supply reliability on a retail firm's performance under joint marketing and inventory decisions. The firm sells a product in a single selling season and can exert marketing effort to influence consumer demand. We develop a modeling framework to quantify the value of improving supply reliability and investigate how this value depends on different model parameters. Our results provide useful insights into how firms should make investment decisions on adopting new technologies to improve supply reliability. First, we establish a necessary and sufficient condition under which the maximum unit cost a firm is willing to pay to improve supply reliability increases in product price. We further show that this condition would hold in most practical situations. Thus, with some caveats, our result supports the intuition that a firm is willing to pay more to improve supply reliability for products with a higher price. Next we show that for two products with the same price, a firm is willing to pay more to improve supply reliability for the product with a higher product cost. This implies that it is not necessarily true that emerging technologies for improving supply reliability should be first adopted for products with the highest unit contribution margin. Finally, we show that a product with a lower marketing cost function always benefits more from improved supply reliability than a product with a higher marketing cost function. This finding suggests that the priority of adopting new technologies should be given to situations where the firm can effectively induce greater demand through promotional effort.

  


 

Jay Simon, PhD Student
Title:  “Decision Making with Prostate Cancer: A Multiple-Objective Model with Uncertainty”
Accepted at: Interfaces 
November 2008
 
A man diagnosed with prostate cancer faces a difficult decision. Treatments have varying cure rates and a wide range of side effects. This paper discusses a multiple-objective decision model under uncertainty, which will be shaped by the preferences and personal characteristics of the individual. This quantitative process incorporates both user input and medical data, and allows an individual prostate cancer patient to meaningfully compare treatments. In addition to expected utilities, the model also provides intermediate results which allow for user feedback and increase the transparency of the analysis.