A Heuristic for Moment-Matching Scenario Generation
Tóm tắt
In stochastic programming models we always face the problem of how to represent the random variables. This is particularly difficult with multidimensional distributions. We present an algorithm that produces a discrete joint distribution consistent with specified values of the first four marginal moments and correlations. The joint distribution is constructed by decomposing the multivariate problem into univariate ones, and using an iterative procedure that combines simulation, Cholesky decomposition and various transformations to achieve the correct correlations without changing the marginal moments. With the algorithm, we can generate 1000 one-period scenarios for 12 random variables in 16 seconds, and for 20 random variables in 48 seconds, on a Pentium III machine.
Tài liệu tham khảo
D.R. Cariño and W.T. Ziemba, “Formulation of the Russell-Yasuda Kasai financial planning model,” Operations Research, vol. 46, no. 4, pp. 443-449, 1998.
G. Consigli and M.A.H. Dempster, “Dynamic stochastic programming for asset-liability management,” Annals of Operations Research, vol. 81, pp. 131-162, 1998.
C. Dert, “Asset liability management for pension funds, a multistage chance constrained programming approach,” PhD Thesis, Erasmus University, Rotterdam, The Netherlands, 1995.
A.I. Fleishman, “A method for simulating nonnormal distributions,” Psychometrika, vol. 43, pp. 521-532, 1978.
N.J. Higham, “Computing the nearest correlation matrix—Aproblem from finance,” Numerical Analysis Report No. 369, Manchester Centre for Computational Mathematics, Manchester, England, 2000.
K. HØyland and S.W. Wallace, “Generating scenario trees for multistage decision problems,” Management Science, vol. 47, no. 2, pp. 295-307, 2001.
P.M. Lurie and M.S. Goldberg, “An approximate method for sampling correlated random variables from partially-specified distributions,” Management Science, vol. 44, no. 2, pp. 203-218, 1998.
J.M. Mulvey, “Generating scenarios for the Towers Perrin investment system,” Interfaces, vol. 26, pp. 1-13, 1996.
C.D. Vale and V.A. Maurelli, “Simulating multivariate nonnormal distributions,” Psychometrika, vol. 48, no. 3, pp. 465-471, 1983.