Numerische Mathematik

, Volume 55, Issue 2, pp 137–157 | Cite as

A Monte Carlo method for high dimensional integration

  • Yosihiko Ogata
Article

Summary

A new method for the numerical integration of very high dimensional functions is introduced and implemented based on the Metropolis' Monte Carlo algorithm. The logarithm of the high dimensional integral is reduced to a 1-dimensional integration of a certain statistical function with respect to a scale parameter over the range of the unit interval. The improvement in accuracy is found to be substantial comparing to the conventional crude Monte Carlo integration. Several numerical demonstrations are made, and variability of the estimates are shown.

Subject Classifications

AMS(MOS): 65D30 CR: G1.4 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Metropolis, N., Rosenbluth, A.W., Rosenbluth, M.N., Teller, A.H., Teller, E.: Equation of state calculations by fast computing machines. J. Chem. Phys.21, 1087–1092 (1953)Google Scholar
  2. Ogata, Y.: A Monte Carlo method for the objective Bayesian procedure. Research Memorandum No. 347, The Institute of Statistical Mathematics, Tokyo 1988Google Scholar
  3. Ogata, Y., Tanemura, M.: Approximation of likelihood function in estimating the interaction potentials from spatial point patterns. Research Memorandum No. 216, The Institute of Statistical Mathematics, Tokyo 1981Google Scholar
  4. Ogata, Y., Tanemura, M.: Likelihood analysis of spatial point patterns. Research Memorandum No. 241, The Institute of Statistical Mathematics, Tokyo 1984aGoogle Scholar
  5. Ogata, Y., Tanemura, M.: Likelihood analysis of spatial point patterns. J.R. Statist. Soc. B46, 496–518 (1984b)Google Scholar
  6. Ogata, Y., Tanemura, M.: Likelihood estimation of soft-core interaction potentials for Gibbsian point patterns. Ann. Inst. Statist. Math. (1988)Google Scholar
  7. Hammersley, J.M., Handscomb, D.C.: Monte Carlo Methods. London: Methuen & Co Ltd (1964)Google Scholar
  8. Ripley, B.D.: Simulating spatial patterns: dependent samples from a multivariate density. Appl. Statist.28, 109–112 (1979)Google Scholar
  9. Wood, W.W.: Monte Carlo studies of simple liquid models. In: Temperley, H.N.V., Rowlinson, J.S., Rushbrooke, G.S. (eds.) Physics of simple liquids, Chap. 5, pp. 115–230, Amsterdam: NorthHolland (1968)Google Scholar

Copyright information

© Springer-Verlag 1989

Authors and Affiliations

  • Yosihiko Ogata
    • 1
  1. 1.The Institute of Statistical MathematicsTokyo 106Japan

Personalised recommendations