Path dependence and biases in the even swaps decision analysis method

There are usually multiple paths that can be followed in a decision analysis process. It is possible that these different paths lead to different outcomes, i.e. there can exist path dependence. To demonstrate the phenomenon we show how path dependence emerges in the Even Swaps method. We also discuss the phenomenon in decision analysis in general. The Even Swaps process helps the decision maker to find the most preferred alternative out of a set of multi-attribute alternatives. In our experiment different paths are found to systematically lead to different choices in the Even Swaps process. This is explained by the accumulated effect of successive biased even swap tasks. The biases in these tasks are shown to be due to scale compatibility and loss aversion phenomena. Estimates of the magnitudes of these biases in the even swap tasks are provided. We suggest procedures to cancel out the effects of biases.

[1]  D. Winterfeldt,et al.  Cognitive and Motivational Biases in Decision and Risk Analysis , 2015, Risk analysis : an official publication of the Society for Risk Analysis.

[2]  Tuomas J. Lahtinen,et al.  Path dependence in Operational Research—How the modeling process can influence the results , 2016 .

[3]  T. Saaty.  How to Make a Decision: The Analytic Hierarchy Process , 1990 .

[4]  John W. Payne,et al.  Measuring Constructed Preferences: Towards a Building Code , 1999 .

[5]  James Corner,et al.  The effects of anchoring in interactive MCDM solution methods , 1997, Comput. Oper. Res..

[6]  P. Slovic.  The Construction of Preference , 1995 .

[7]  Hans Vrolijk,et al.  Behavioral and procedural consequences of structural variation in value trees , 2001, Eur. J. Oper. Res..

[8]  A. Tversky,et al.  Loss Aversion in Riskless Choice: A Reference-Dependent Model , 1991 .

[9]  Kathryn B. Laskey,et al.  Estimating utility functions in the presence of response error , 1987 .

[10]  Raimo P. Hämäläinen,et al.  A Preference Programming Approach to Make the Even Swaps Method Even Easier , 2005, Decis. Anal..

[11]  Igor Linkov,et al.  Multi-criteria decision analysis in environmental sciences: ten years of applications and trends. , 2011, The Science of the total environment.

[12]  Benjamin F. Hobbs,et al.  Quantifying and Mitigating the Splitting Bias and Other Value Tree-Induced Weighting Biases , 2007, Decis. Anal..

[13]  Ralph L. Keeney,et al.  Book Reviews : Scientific Opportunities and Public Needs: Improv ing Priority Setting and Public Input at the National Institutes of Health. Institute of Medicine. Washington, DC: National Academy Press, 1998, 136 pages, $26.00 , 1998 .

[14]  John R. Doyle,et al.  A comparison of three weight elicitation methods: good, better, and best , 2001 .

[15]  William T. Morris,et al.  On the Art of Modeling , 1967 .

[16]  Robin Gregory,et al.  Structured Decision Making: A Practical Guide to Environmental Management Choices , 2012 .

[17]  Raimo P. Hämäläinen,et al.  On the convergence of multiattribute weighting methods , 2001, Eur. J. Oper. Res..

[18]  Raimo P. Hämäläinen,et al.  The threat of weighting biases in environmental decision analysis , 2008 .

[19]  Pekka Korhonen,et al.  Choice behavior in interactive multiple-criteria decision making , 1990 .

[20]  Kurt A. Carlson,et al.  Improving Preference Assessment: Limiting the Effect of Context Through Pre-exposure to Attribute Levels , 2006, Manag. Sci..

[21]  J. L. Pinto,et al.  Loss aversion and scale compatibility in two-attribute trade-offs , 2002 .

[22]  Robert T. Clemen,et al.  Toward an Improved Methodology to Construct and Reconcile Decision Analytic Preference Judgments , 2013, Decis. Anal..

[23]  D. Winterfeldt,et al.  The effects of splitting attributes on weights in multiattribute utility measurement , 1988 .

[24]  Peter P. Wakker,et al.  Making Descriptive Use of Prospect Theory to Improve the Prescriptive Use of Expected Utility , 2001, Manag. Sci..

[25]  A. Tversky,et al.  Contingent weighting in judgment and choice , 1988 .

[26]  R. L. Keeney,et al.  Decisions with Multiple Objectives: Preferences and Value Trade-Offs , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[27]  J S Hammond,et al.  Even swaps: a rational method for making trade-offs. , 1998, Harvard business review.

[28]  Q. Mcnemar.  Note on the sampling error of the difference between correlated proportions or percentages , 1947, Psychometrika.

[29]  Simon French,et al.  Interactive Multi-Objective Programming: Its Aims, Applications and Demands , 1984 .

[30]  Philippe Delquié,et al.  Inconsistent trade-offs between attributes: new evidence in preference assessment biases , 1993 .

[31]  Benjamin F. Hobbs,et al.  Using a Bayesian Approach to Quantify Scale Compatibility Bias , 2002, Manag. Sci..

[32]  Philippe Delquié,et al.  Bi-Matching: A New Preference Assessment Method to Reduce Compatibility Effects , 1997 .

[33]  Warren E. Walker,et al.  Does the best practice of rational-style model-based policy analysis already include ethical considerations? , 2009 .

[34]  W. Edwards,et al.  Decision Analysis and Behavioral Research , 1986 .

[35]  Jean-Louis Malouin,et al.  Model validation in operations research , 1983 .

[36]  Raimo P. Hämäläinen,et al.  Smart-Swaps - A decision support system for multicriteria decision analysis with the even swaps method , 2007, Decis. Support Syst..

[37]  Raimo P. Hämäläinen,et al.  On the importance of behavioral operational research: The case of understanding and communicating about dynamic systems , 2013, Eur. J. Oper. Res..