Dissertation/Thesis Abstract

Quantitative approach to technical performance measurement and technical risk analysis utilizing Bayesian methods and Monte Carlo simulation
by Lewis, Tiffany Lorraine, Ph.D., The George Washington University, 2010, 290; 3397235
Abstract (Summary)

Risk on a project or program is typically evaluated in terms of the triple constraint: scope, time, and cost. The Monte Carlo method (Metropolis & Ulam, 1949) is a widely accepted risk analysis technique and is deemed to be an effective way of analyzing the uncertainty associated with cost and schedule risks. More systems engineers and risk managers are taking advantage of this risk analysis technique to perform independent risk assessments on either cost or schedule; however, the analysis of technical risk using a statistical approach has not been formulated to a significant degree in the literature.

This research study will explore the use of a statistical versus a deterministic approach to independently assess the risks associated with technical performance. The methodology discussed transforms a deterministic risk assessment model into a statistical model. Expert judgment is used within a Bayesian framework to develop baseline expected values for technical performance. Technical Performance Measurement (TPM), Monte Carlo simulation, and @Risk software are used to calculate a system level Technical Risk Index Distribution (TRID). The TRID framework defines distribution ranges for each TPM and formulates risk index distributions. Actual data from a DoD TPM implementation project is used to validate the TRID framework. The proposed statistical model is verified on a hypothetical system where quantifiable TPMs have been identified that meet the criterion in the model proposed.

Keywords. Monte Carlo simulation, TPMs, technical performance measures, technical risk, technical performance risk, Monte Carlo risk analysis, sensitivity analysis, technical risk analysis, program management, risk management, project management, risk analysis, risk, quantitative risk analysis, expert judgment, Bayes Theorem, Bayesian methods, expert opinion.

Indexing (document details)
Advisor: Mazzuchi, Thomas A., Sarkani, Shahram
Commitee: Allario, Frank, Murphree, Edward L., Podolsky, Michael J.
School: The George Washington University
Department: Engineering Mgt and Systems Engineering
School Location: United States -- District of Columbia
Source: DAI-B 71/04, Dissertation Abstracts International
Subjects: Statistics, Systems science, Operations research
Keywords: Bayesian methods, Expert judgment, Monte Carlo simulation, Risk analysis, Technical performance measurement, Technical risk
Publication Number: 3397235
ISBN: 978-1-109-68946-4
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy