Taking the Next Step: Turning OLS CER-Based Estimates into Risk Distributions
There has been an increased focused on uncertainty and risk in cost estimates as customers now routinely desire a range of potential costs, rather than a point estimate,. Most analysts know that when performing regression analysis the uncertainty of the estimate can be derived from the analysis of variance (ANOVA) statistics; however, only rarely is this uncertainty modeled in the risk analysis. This paper will touch briefly on the concepts behind the prediction interval, and then will delve into a deeper discussion of how prediction intervals can be converted into uncertainty distributions for estimates generated from regression-based cost estimating relationships (CERs). The paper will give examples for estimates produced using linear and non linear ordinary least squares (OLS) regressions. The paper will conclude with a short discussion of how the distributions can be modeled in a Monte Carlo simulation.
Christina M. Kanick graduated from the University of Pittsburgh in 2006 with a B.S. in Industrial Engineering. Over the past year, she has been employed by Northrop Grumman as an Operations Research Analyst. She supports the CG(X) Team conducting cost and risk analysis. She has performed research for the Air Force Cost Analysis Agency (AFCAA) to develop cost estimating relationships (CERs). In addition, Ms. Kanick was a member of the TASC proposal support team, which was called in by the Northrop Grumman Corporate Staff, in the KC-30 Tanker, as well as the DD(X) Independent Cost Evaluation Team and on other Independent Cost Evaluations (ICEs) in addition to performing risk analysis for Intelligence Community customers.
Eric R. Druker graduated from the College of William and Mary with a B.S. in Applied Mathematics in 2005 concentrating in both Operations Research and Probability & Statistics with a minor in Economics. He is employed by Northrop Grumman as a Technical & Research lead. He performs cost and risk analysis on several programs within both the Intelligence and DoD communities. He was a recipient of the 2005 NGIT President’s award for his work on Independent Cost Evaluations during which he helped to develop the risk process currently used by NGIT’s ICE teams. As a member of Northrop Grumman’s ICE working group, he has helped shape the cost and risk practices used on independent cost estimates and evaluations across the corporation. In addition to SCEA conferences, Eric has also presented papers at the Naval Postgraduate School’s Acquisition Research Symposium, DoDCAS and the NASA PM Challenge. He has also performed decision tree analysis for NG Corporate law and built models for Hurricane Katrina Impact Studies and Schedule/Cost Growth determination.
Richard L. Coleman is a 1968 Naval Academy graduate, received an M. S. with Distinction from the U. S. Naval Postgraduate School and retired from active duty as a Captain, USN, in 1993. His service included tours as Commanding Officer of USS Dewey (DDG 45), and as Director, Naval Center for Cost Analysis. He has worked extensively in cost, CAIV, and risk for the Missile Defence Agency (MDA), Navy ARO, the intelligence community, NAVAIR, and the DD(X) Design Agent team. He has supported numerous ship programs including DD(X), the DDG 51 class, Deepwater, LHD 8 and LHA 6, the LPD 17 class, Virginia class submarines, CNN 77, and CVN 21. He is the Director of the Cost and Price Analysis Center of Excellence and conducts Independent Cost Evaluations on Northrop Grumman programs. He has more than 65 professional papers to his credit, including five ISPA/SCEA and SCEA Best Paper Awards and two ADoDCAS Outstanding Contributed Papers. He was a senior reviewer for all the SCEA CostPROF modules and lead author of the Risk Module. He has served as Regional and National Vice President of SCEA and is currently a Board Member.
Peter J. Braxton holds an AB in Mathematics from Princeton University and an M.S. in Applied Science (Operations Research) from the College of William and Mary.
He has worked to advance the state of knowledge of cost estimating, Cost As an Independent Variable (CAIV), Target Costing, and risk analysis on behalf of the Navy Acquisition Reform Office (ARO), the DD(X) development program, and other ship and intelligence community programs. He has co-authored several professional papers, including ISPA/SCEA International Conference award-winners in CAIV (1999) and Management (2005). He served as managing editor for the original development of the acclaimed Cost Programmed Review Of Fundamentals (CostPROF) body of knowledge and training course materials and is currently undertaking to lead a large team of cost professional in a comprehensive update thereof. He serves as SCEA’s Director of Training, a Northrop Grumman Technical Fellow, and Director of Research within TASC’s Management Consulting Division. He was named SCEA’s 2007 Estimator of the Year for contributions in Education.
Matthew M. Cain graduated from James Madison University with B.S. degrees in Quantitative Finance and Economics with a minor in Mathematics. As an Operations Research analyst employed by Northrop Grumman, Matt has performed cost and risk analysis for many ship programs and proposals including CG(X), LPD 22, LHA 6, UCAS-D, and DDG 1000. Along with his ship work, Matt has been apart of numerous Independent Cost Evaluation (ICE) teams as well as proposal teams developing basis of estimates (BOEs).