Posted by Here, There Be Dragons: Considering the Right Tail in Risk Management
Risk Track
Downloadable Files:
Abstract:
The portfolio effect is the reduction of risk achieved by funding multiple projects that are not perfectly correlated with one another. It is relied upon in setting confidence level policy for programs that consist of multiple projects. The idea of a portfolio effect has its roots in modern finance as pioneered by Nobel Memorial Prize winner Harry Markowitz. However, in three recent ISPA-SCEA conference presentations, “The Portfolio Reconsidered” in 2007, “The Fractal Geometry of Cost Risk” in 2008, and “The Portfolio Effect and the Free Lunch” in 2009, the author has demonstrated that the portfolio effect is more myth than fact. However, current NASA and Department of Defense policy guidance relies heavily upon this chimerical effect.
This is seen in policy that sets funding at a set percentile, typically at the 70th or 80th percentile. The inherent, optimistic belief is that the portfolio effect will allow total funding agency-wide to be much higher, above the 90th percentile. However, in the absence of such an effect, policy guidance that specifies funding at a relatively low percentile, like the 70th or 80th, will result in numerous overruns, insufficient reserves, and other financial difficulties at the agency level.
Funding at such levels will result in overruns for 20-30% of missions, so cost growth will be a common occurrence. And by funding only at a percentile, there is no insight into how much will be needed in extra reserves. Depending upon the variance of the cost risk distribution and other characteristics, such as skewness and kurtosis, this amount can vary significantly. Thus the right tail must be taken into consideration when establishing reserves. A superior alternative has been proposed that measures this expected shortfall, called Tail Value at Risk. Also called conditional tail expectation, its use is growing in popularity in a variety of industries, including insurance.
Recently, the notion of coherence has been proposed and adopted for risk measures. The notion of coherence is discussed, and its relevance to Value at Risk and Tail Value at Risk is examined.
Author:
Christian Smart
Missile Defense Agency
Dr. Christian Smart is currently employed as a senior operations research analyst with the Missile Defense Agency. An experienced estimator and analyst, he is deputy division chief for sensors cost estimating. He was responsible for risk analysis and cost integration for NASA’s Ares launch vehicles. Dr. Smart spent several years overseeing the development of the NASA/Air Force Cost Model and has developed numerous cost models and techniques that are used by Goddard Space Flight Center, Marshall Space Flight Center, and NASA HQ. Dr. Smart is a past president of the Greater Alabama Chapter of SCEA, and is the managing editor for The Journal of Cost Analysis and Parametrics. He has given numerous presentations on cost modeling and risk analysis both in the U.S. and abroad. Dr. Smart was cited as 2006 Professional of the Year for the Greater Alabama Chapter of SCEA and was awarded best of conference paper at the 2008 Annual Joint ISPA-SCEA conference in Noordwijk for “The Fractal Geometry of Cost Risk” and best of conference paper at the 2009 Annual Joint ISPA-SCEA conference in St. Louis for “The Portfolio Effect and the Free Lunch.” In addition, he was named ISPA’s Parametrician of the Year in 2009. He is a SCEA certified cost estimator/analyst (CCEA), a member of the Society for Cost Estimating and Analysis (SCEA) and the International Society of Parametric Analysts (ISPA). Dr. Smart earned bachelors degrees in Economics and Mathematics from Jacksonville State University, and a Ph.D. in Applied Mathematics from the University of Alabama in Huntsville.