Date of Award
Master of Science
Department of Mathematics and Statistics
Edward D. White, PhD
Efficient decision making mandates the accuracy of forecasted estimations of a contract's final value known within Earned Value Management (EVM) as the Estimates at Completion (EAC). Our research evaluates the prospect of nonlinear growth modeling as an alternative to the current predictive tools used for calculating EAC, such as the Cost Performance Index (CPI), the Schedule Cost Index (SCI), and the Composite Index methods. Our study uses the Gompertz growth curve to produce three EAC Models based on contract phase: A Production Model, a Development Model, and a Combined Model. Contract Performance Report (CPR) data are used to develop the models. Mean Absolute Percentage Error (MAPE) is used to evaluate and select the more accurate model's EAC. We compare along three datasets for performance evaluation: a model building dataset, an additional dataset, and a dataset of designated Over Target Baseline (OTB) contracts. For 63% to 79% of OTB contracts, depending on model and phase examined, our study shows all three growth models out perform all three Index-based methods. Our research shows growth models as a more accurate estimating tool for identified OTB contract's EAC as compared to the CPI, SCI, and Composite Index methods.
DTIC Accession Number
Trahan, Elizabeth N., "An Evaluation of Growth Models as Predictive Tools for Estimates at Completion (EAC)" (2009). Theses and Dissertations. 2461.