Remote Access Proceedings of the American Mathematical Society
Green Open Access

Proceedings of the American Mathematical Society

ISSN 1088-6826(online) ISSN 0002-9939(print)

 
 

 

Hilbert space analysis of Latin Hypercube Sampling


Author: Peter Mathé
Journal: Proc. Amer. Math. Soc. 129 (2001), 1477-1492
MSC (2000): Primary 65C05; Secondary 62D05
DOI: https://doi.org/10.1090/S0002-9939-00-05850-0
Published electronically: October 24, 2000
MathSciNet review: 1814176
Full-text PDF

Abstract | References | Similar Articles | Additional Information

Abstract: Latin Hypercube Sampling is a specific Monte Carlo estimator for numerical integration of functions on ${\mathbb R}^{d}$ with respect to some product probability distribution function. Previous analysis established that Latin Hypercube Sampling is superior to independent sampling, at least asymptotically; especially, if the function to be integrated allows a good additive fit. We propose an explicit approach to Latin Hypercube Sampling, based on orthogonal projections in an appropriate Hilbert space, related to the ANOVA decomposition, which allows a rigorous error analysis. Moreover, we indicate why convergence cannot be uniformly superior to independent sampling on the class of square integrable functions. We establish a general condition under which uniformity can be achieved, thereby indicating the rôle of certain Sobolev spaces.


References [Enhancements On Off] (What's this?)

  • 1. Robert A. Adams.
    Sobolev spaces.
    Academic Press [A subsidiary of Harcourt Brace Jovanovich, Publishers], New York-London, 1975.
    Pure and Applied Mathematics, Vol. 65. MR 56:9247
  • 2. E. B. Davies.
    Heat kernels and spectral theory.
    Cambridge University Press, Cambridge, 1990. MR 92a:35035
  • 3. J. Diestel and J. J. Uhl, Jr.
    Vector measures.
    American Mathematical Society, Providence, R.I., 1977.
    With a foreword by B. J. Pettis, Mathematical Surveys, No. 15. MR 56:12216
  • 4. R. E. Edwards.
    Functional Analysis. Theory and Applications.
    Holt, Rinehart & Winston, New York, Chicago, 1965. MR 36:4308
  • 5. B. Efron and C. Stein.
    The jackknife estimate of variance.
    Ann. Statist., 9(3):586-596, 1981. MR 82k:62074
  • 6. George S. Fishman.
    Monte Carlo. Concepts, algorithms, and applications, Springer-Verlag, New York, 1996. MR 97g:65019
  • 7. R. L. Iman and W. J. Conover.
    Small sample sensitivity analysis techniques for computer models, with an application to risk assessment.
    Comm. Statist., Part A: Theory and Methods, 9:1749-1874, 1980. MR 81m:65012
  • 8. Malvin H. Kalos and Paula A. Whitlock.
    Monte Carlo methods. Vol. I.
    John Wiley & Sons Inc., New York, 1986.
    Basics. MR 88e:65009
  • 9. L. V. Kantorovich and G. P. Akilov.
    Funktsionalny{\u{\i}}\kern.15emanaliz.
    ``Nauka'', Moscow, third edition, 1984. MR 86m:46001
  • 10. Michel Ledoux and Michel Talagrand.
    Probability in Banach spaces.
    Isoperimetry and processes, Springer-Verlag, Berlin, 1991. MR 93c:60001
  • 11. W.-L. Loh.
    On Latin Hypercube Sampling.
    Ann. Statist., 24:2058-2080, 1996. MR 98k:62008
  • 12. M. D. McKay, W. J. Conover, and R. J. Beckman.
    A comparison of three methods for selecting values of output variables in the analysis of output from a computer code.
    Technometrics, 21:239-245, 1979. MR 80k:65012
  • 13. D. S. Mitrinovic, J. E. Pecaric, and A. M. Fink.
    Classical and new inequalities in analysis.
    Kluwer Academic Publishers Group, Dordrecht, 1993. MR 94c:00004
  • 14. J. Neveu.
    Bases Mathématiques du Calcul des Probabilités.
    Maison et Cie, 1964. MR 33:6659
  • 15. Erich Novak.
    Deterministic and stochastic error bounds in numerical analysis.
    Lect. Notes Math. 1349. Springer-Verlag, Berlin, 1988. MR 90a:65004
  • 16. A. B. Owen.
    A Central Limit Theorem for Latin Hypercube Sampling.
    J. R. Statist. Soc. B, 54:541-551, 1992. MR 93j:62047
  • 17. Art B. Owen.
    Monte Carlo variance of scrambled net quadrature.
    SIAM J. Numer. Anal., 34(5):1884-1910, 1997. MR 98h:65006
  • 18. H. L. Royden.
    Real analysis.
    Macmillan Publishing Company, New York, third edition, 1988. MR 90g:00004
  • 19. L. Saloff-Coste.
    Lectures on finite Markov chains.
    In Lectures on probability theory and statistics (Saint-Flour, 1996), pages 301-413. Springer, Berlin, 1997. MR 99b:60119
  • 20. M. Stein.
    Large sample properties of simulations using Latin Hypercube Sampling.
    Technometrics, 29:143-151, 1987. MR 88e:62055; correction MR 91j:62023
  • 21. H. Triebel.
    Höhere Analysis.
    VEB Deutscher Verlag der Wissenschaften, Berlin, 1972.
    Hochschulbücher für Mathematik, Band 76. MR 50:12511
  • 22. N.N. Vakhania, V. I. Tarieladze, and S.A. Chobanjan.
    Probability Distributions on Banach Spaces.
    D. Reidel, Dordrecht, Boston, Lancaster, Tokyo, 1987. MR 97k:60007

Similar Articles

Retrieve articles in Proceedings of the American Mathematical Society with MSC (2000): 65C05, 62D05

Retrieve articles in all journals with MSC (2000): 65C05, 62D05


Additional Information

Peter Mathé
Affiliation: Weierstrass–Institute for Applied Analysis and Stochastics, Mohrenstraße 39, D– 10117 Berlin, Germany
Email: mathe@wias-berlin.de

DOI: https://doi.org/10.1090/S0002-9939-00-05850-0
Keywords: Latin Hypercube Sampling, stratified sampling, asymptotic variance
Received by editor(s): August 25, 1999
Published electronically: October 24, 2000
Communicated by: David Sharp
Article copyright: © Copyright 2000 American Mathematical Society

American Mathematical Society