This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Decision Analysis Vol. 1, No. 2, June 2004, pp. 71–78 issn 1545-8490 eissn 1545-8504 04 0102 0071 inf orms ® doi 10.1287/deca.1030.0005 © 2004 INFORMS Speaking of Decisions: Precise Decision Language Ronald A. Howard Department of Management Science and Engineering, School of Engineering, Stanford University, Stanford, California 94305-4026, [email protected] T his paper presents the current state of evolution of a language for teaching and practicing decision analysis that may avoid confusion of students, clients, and ourselves. Many of the terms currently used are inaccu- rate, arcane, or unnecessary. Restricting decision language to terms that are accurate, familiar, and fundamental contributes to clarity of thought and understanding. To illustrate the type of changes advocated, I propose replacing dependence with relevance , expectation with e-value , utility with u-value , and eschewing subjective proba- bility , confidence , uncertainty about probability , any distinction between risk and uncertainty , and states of nature . I show how to incorporate the new terminology in teaching and practice. Key words : clairvoyant; clarity; decision analysis; diagrams; distinctions; language; relevance; uncertainty History : Received on June 9, 2001. Accepted by Robert T. Clemen and Don N. Kleinmuntz on July 9, 2003, without revision. This paper was refereed. Introduction In my classes, I tell the story of a consulting trip I made to the Netherlands in the 1960s. One day I spotted a set of colorful plastic blocks in a wooden case in a toy store. They could be snapped together to make many toys. I brought the box home to my children and they became some of the first kids in the United States to play with “Legos.” Now every- one is familiar with them. I asked myself why, as a child, I did not have Legos but rather Erector sets and Tinkertoys, and I ask the same question of my class. Students quickly agree that the answer is not simply “plastics,” for they existed in my childhood. They also agree on the performance requirements: The blocks must be easy for a child to snap together, and yet they must hold well so that the wings of “airplanes” do not readily fall off. Usually someone comes up with the answer “precision plastic molding,” for the per- formance requirements dictate that the dimensions of the blocks be precise. Then, I tell the class that I am going to develop the concepts and language of deci- sion making following the design principles of Legos. I shall define all of our components so precisely that they will easily fit together and yet the final structure of thought will be sturdy and thus able to support the challenges it may face. This paper describes the evolution and current state of that pursuit....
View Full Document
This note was uploaded on 06/16/2010 for the course MS&E 352 taught by Professor Ronhoward during the Winter '09 term at Stanford.
- Winter '09