Decision Analysis and Validation of Value Focused Thinking Decision Models Using Multivariate Analysis Techniques

Abstract

Decision Analysis (DA) is a useful tool to assist decision makers (DM) with difficult and complex decisions using mathematical models. Value Focused Thinking (VFT) models are a useful DA tool widely employed in the Air Force. However, VFT models are rarely validated. This research will attempt to validate any given VFT model and provide insight into the discriminating attributes of the alternative set. First, a two group discriminant analysis is applied the alternative set given the prior knowledge of the selected alternatives. Next, compromise programming is used attempt to minimize the distance between the posterior probability of an alternative being selected and its current weighted value by varying the weights. This set of optimized weights is then used in the two group discriminant analysis to classify the alternative set and attempt to validate the VFT model by selecting the same subset of alternatives chosen by the DM. Additionally, this process will provide insight into what attributes of a given alternative set are actually the discriminating factors in the decision which may or may not be the attributes that are most important to or most heavily weighted by the DM.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 24, 2011
Accession Number
ADA540067

Entities

People

  • James L. Pruitt

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Counter IED
  • Human Systems

DTIC Thesaurus Topics

  • Air Force
  • Computer Programming
  • Computers
  • Data Science
  • Discriminant Analysis
  • Engineering
  • Equations
  • Information Science
  • Literature Surveys
  • Mathematical Models
  • Mathematical Programming
  • Multivariate Analysis
  • Neural Networks
  • Operations Research
  • Probability
  • Thinking
  • Validation

Readers

  • Computational Modeling and Simulation
  • Defense Acquisition Program Management
  • Statistical inference.