0
Research Papers

# A Use of a Mathematical Model in Updating Concept Selection

[+] Author and Article Information
Shun Takai

Department of Mechanical and Aerospace Engineering, Missouri University of Science and Technology, 290C Toomey Hall, 400 West 13th Street, Rolla, MO 65409-0500takais@mst.edu

J. Mech. Des 132(10), 101009 (Oct 05, 2010) (10 pages) doi:10.1115/1.4001974 History: Received September 20, 2009; Revised May 10, 2010; Published October 05, 2010; Online October 05, 2010

## Abstract

This paper presents the use of a mathematical model in updating a decision maker’s belief before selecting a product/system concept and demonstrates a procedure to calculate the maximum monetary value of such a model in terms of the expected value of information. Acquiring information about uncertainty and updating belief according to the new information is an important step in concept selection. However, obtaining additional information can be considered beneficial only if the acquisition cost is less than the benefit. In this paper, a mathematical model is used as an information source that predicts outcomes of an uncertainty. The prediction, however, is imperfect information because the model is constructed based on simplifying assumptions. Thus, the expected value of imperfect information needs to be calculated in order to evaluate the tradeoff between the accuracy and the cost of model prediction (information). The construction and analysis of a mathematical model, the calculation of the expected value of information (model prediction) and updating the belief based on the model prediction are illustrated using a concept selection for a public project.

<>

## Figures

Figure 1

Decision tree for the expected value of information calculation

Figure 2

Influence diagram for a public project

Figure 3

Decision tree for a public project (without information)

Figure 4

Decision tree after decomposition

Figure 5

Belief updating: (a) initial probability tree and (b) flipped probability tree

Figure 6

Prior P(r=R)

Figure 7

Likelihood P(“r=R”∣r=R)

Figure 8

Joint probability P(“r=R” and r=R)

Figure 9

Flipped joint probability P(r=R and “r=R”)

Figure 10

Preposterior P(r=R)

Figure 11

Posterior P(r=R∣“r”=R)

Figure 12

Decision tree with and without information

Figure 13

Expected value of information

Figure 14

Updated concept selection

Figure 15

Expected utility: (a) without information and (b) with information “r=95” of accuracy α=0.9

## Errata

Some tools below are only available to our subscribers or users with an online account.

### Related Content

Customize your page view by dragging and repositioning the boxes below.

Topic Collections