Diffusion Simulation via Green Function Evaluation

Abstract

In the present paper, a scheme of path sampling is explored for stochastic diffusion processes. The core issue is the evaluation of the diffusion propagators (spatial–temporal Green functions) by solving the corresponding Kolmogorov forward equations with Dirac delta functions as initials. The technique can be further used in evaluating general functional of path integrals. The numerical experiments demonstrated that the simulation scheme based on this approach overwhelms the popular Euler scheme and Exact Algorithm in terms of accuracy and efficiency in fairly general settings. An example of likelihood inference for the diffusion driven Cox process is provided to show the scheme’s potential power in applications.

Keywords

Cox process / Kolmogorov forward equation / Killing diffusion process / Stochastic diffusion process / Sample path simulation / Monte Carlo calculation

References

[1] Albanese, C., Lawi, S.: Laplace transforms for integrals of Markov processes. arXiv preprint arXiv:0710.1599 (2007)

[2] Beskos A, Roberts GO. Exact simulation of diffusions. Ann. Appl. Probab.. 2005, 15 4 2422-2444

[3] Beskos A, Papaspiliopoulos O, Roberts GO. Retrospective exact simulation of diffusion sample paths with applications. Bernoulli. 2006, 12 6 1077-1098

[4] Beskos A, Papaspiliopoulos O, Roberts GO. A factorisation of diffusion measure and finite sample path constructions. Methodol. Comput. Appl. Probab.. 2008, 10 1 85-104

[5] Cox DR. Some statistical methods connected with series of events. J. R. Stat. Soc. Ser. B (Methodol.). 1955, 17 2 129-157

[6] Clifford P, Wei G. The equivalence of the cox process with squared radial Ornstein-Uhlenbeck intensity and the death process in a simple population model. Ann. Appl. Probab.. 1993, 3 3 863-873

[7] Friedman, A.: Stochastic Differential Equations and Applications. Probability and Mathematical Statistics Series 28, vol. Volume 1. Academic Press, New York (1975)

[8] Hirsa A. Computational Methods in Finance. 2012 Boca Raton: CRC Press

[9] Hurn, A., Jeisman, J., Lindsay, K., et al.: Teaching an old dog new tricks improved estimation of the parameters of stochastic differential equations by numerical solution of the Fokker–Planck equation. Queensland University of Technology, Brisbane, Manuscript (2006)

[10] Hurn AS, Jeisman JI, Lindsay KA. Seeing the wood for the trees: a critical evaluation of methods to estimate the parameters of stochastic differential equations. J. Financ. Economet.. 2007, 5 3 390-455

[11] Hurd TR, Kuznetsov A. Explicit formulas for Laplace transforms of stochastic integrals. Markov Process. Related Fields. 2008, 14 2 277-290

[12] Iacus SM. Simulation and Inference for Stochastic Differential Equations. Springer Series in Statistics. 2008 New York: Springer

[13] Jensen B, Poulsen R. Transition densities of diffusion processes: numerical comparison of approximation techniques. J. Deriv.. 2002, 9 4 18-32

[14] Kallenberg O. Foundations of Modern Probability. 2006 New York: Springer

[15] Kloeden, P.E., Platen, E., Schurz, H.: Numerical Solution of SDE Through Computer Experiments, Corr. 2nd print edn. Universitext. Springer, Berlin (1997)

[16] Lewis, P.A.W., Shedler, G.S.: Simulation of nonhomogeneous Poisson processes by thinning. Naval Res. Log. Q. 26(3), 403–413

[17] Lo AW. Maximum likelihood estimation of generalized Itô processes with discretely sampled data. Economet. Theory. 1988, 4 2 231-247

[18] Lux T. Inference for systems of stochastic differential equations from discretely sampled data: a numerical maximum likelihood approach. Ann. Finance. 2013, 9 2 217-248

[19] Maruyama G. On the transition probability functions of the Markov process. Nat. Rep. Ochanomizu Univ.. 1954, 5 10-20

[20] Pavliotis, G.A.: Stochastic Processes and Applications: Diffusion Processes, the Fokker–Planck and Langevin Equations. Texts in Applied Mathematics, vol. 60. Springer, New York (2014)

[21] Strikwerda JC. Finite Difference Schemes and Partial Differential Equations. 2004 Philadelphia: SIAM