MML estimation of the parameters of the spherical fisher distribution

  • David L. Dowe
  • Jonathan J. Oliver
  • Chris S. Wallace
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1160)

Abstract

The information-theoretic Minimum Message Length (MML) principle leads to a general invariant Bayesian technique for point estimation. We apply MML to the problem of estimating the concentration parameter, κ, of spherical Fisher distributions. (Assuming a uniform prior on the field direction, μ, MML simply returns the Maximum Likelihood estimate for μ.) In earlier work, we dealt with the von Mises circular case, d=2. We say something about the general case for arbitrary d ≥ 2 and how to derive the MML estimator, but here we only carry out a complete calculation for the spherical distribution, with d=3. Our simulation results show that the MML estimator compares very favourably against the classical methods of Maximum Likelihood and marginal Maximum Likelihood (R.A. Fisher (1953), Schou (1978)). Our simulation results also show that the MML estimator compares quite favourably against alternative Bayesian methods.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J.M. Bernardo and A.F.M. Smith. Bayesian Theory. Wiley, New York, 1994.Google Scholar
  2. 2.
    D.J. Best and N.I. Fisher. The bias of the maximum likelihood estimators of the von Mises-Fisher concentration parameters. Communications in Statistics (B) — Simulation and Computation, B 10(5):493–502, 1981.Google Scholar
  3. 3.
    P. Cheeseman and J. Stutz. Bayesian classification (AUTOCLASS): Theory and results. In U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, editors, Advances in Knowledge Discovery and Data Mining. The AAAI Press, Menlo Park, 1995.Google Scholar
  4. 4.
    D.L. Dowe, L. Allison, T.I. Dix, L. Hunter, C.S. Wallace, and T. Edgoose. Circular clustering of protein dihedral angles by Minimum Message Length. In Proceedings of the 1st Pacific Symposium on Biocomputing (PSB-1), pages 242–255, Hawaii, U.S.A., January 1996.Google Scholar
  5. 5.
    D.L. Dowe, R.A. Baxter, J.J. Oliver, and C.S. Wallace. Point Estimation using the Kullback-Leibler Loss Function and MML. In Proceedings of the Kullback Memorial Research Conference, Washington, D.C., U.S.A., May 1996.Google Scholar
  6. 6.
    D.L. Dowe, J.J. Oliver, R.A. Baxter, and C.S. Wallace. Bayesian estimation of the von Mises concentration parameter. In Proc. 15th Maximum Entropy Conference, Santa Fe, New Mexico, August 1995. Available on the WWW from http://www.cs.monash.edu.au/∼ jono.Google Scholar
  7. 7.
    D.L. Dowe, J.J. Oliver, and C.S. Wallace. MML estimation of the parameters of the spherical von Mises-Fisher distribution. Technical report TR no. 96/272, Dept. of Computer Science, Monash University, Clayton, Victoria 3168, Australia, 1996.Google Scholar
  8. 8.
    D.L. Dowe and C.S. Wallace. Resolving the Neyman-Scott problem by Minimum Message Length. In Proc. Sydney International Statistical Congess (SISC-96), pages 197–198, Sydney, Australia, 1996.Google Scholar
  9. 9.
    N.I. Fisher. Statistical Analysis of Circular Data. Cambridge University Press, 1993.Google Scholar
  10. 10.
    N.I. Fisher, T. Lewis, and B.J.J. Embleton. Statistical Analysis of Spherical Data. Cambridge University Press, Cambridge, 1987.Google Scholar
  11. 11.
    R.A. Fisher. Dispersion on a sphere. Journal of the Royal Statistical Society (Series A), 217:295–305, 1953.Google Scholar
  12. 12.
    H. Jeffreys. An invariant form for the prior probability in estimation problems. Proc. of the Royal Soc. of London A, 186:453–454, 1946.Google Scholar
  13. 13.
    R. Kipling. Just so stories: for little children. Macmillan, 1950.Google Scholar
  14. 14.
    K.V. Mardia. Statistics of Directional Data. Academic Press, 1972.Google Scholar
  15. 15.
    K.V. Mardia. Distribution theory for the von Mises-Fisher distribution and its application. In S. Kotz G. P. Patil and J. K. Ord, editors, Statistical Distributions for Scientific Work, pages 113–130. Reidel, Boston, 1975.Google Scholar
  16. 16.
    R.M. Neal. Bayesian Learning for Neural Networks. PhD thesis, Graduate Dept. of Computer Science, Univ. of Toronto, March 1995.Google Scholar
  17. 17.
    J. Neyman and E.L. Scott. Consistent estimates based on partially consistent observations. Econometrika, 16:1–32, 1948.Google Scholar
  18. 18.
    J. Neyman and E.L. Scott. A theory of the spatial distribution of the galaxies. Astrophysics Journal, 116:144–163, 1952.Google Scholar
  19. 19.
    J.J. Oliver and R.A. Baxter. MML and Bayesianism: Similarities and differences. Technical report TR 206, Dept. of Computer Science, Monash University, Clayton, Victoria 3168, Australia, 1995.Google Scholar
  20. 20.
    J.J. Oliver and D.L. Dowe. Minimum Message Length Mixture Modelling of Spherical von Mises-Fisher distributions. In Proc. Sydney International Statistical Congess (SISC-96), page 198, Sydney, Australia, 1996.Google Scholar
  21. 21.
    J. Rissanen. Stochastic Complexity in Statistical Inquiry. World Scientific, Singapore, 1989.Google Scholar
  22. 22.
    G. Schou. Estimation of the concentration parameter in von Mises-Fisher distributions. Biometrika, 65:369–377, 1978.Google Scholar
  23. 23.
    M.R. Spiegel. Schaum's Outline Series: Theory and Problems of Vector Analysis. McGraw-Hill Book Company, London, 1974.Google Scholar
  24. 24.
    C.S. Wallace. Multiple Factor Analysis by MML Estimation. Technical Report 95/218, Dept. of Computer Science, Monash University, Clayton, Victoria 3168, Australia, 1995.Google Scholar
  25. 25.
    C.S. Wallace and D.M. Boulton. An information measure for classification. Computer Journal, 11:185–194, 1968.Google Scholar
  26. 26.
    C.S. Wallace and D.M. Boulton. An invariant Bayes method for point estimation. Classification Society Bulletin, 3(3):11–34, 1975.Google Scholar
  27. 27.
    C.S. Wallace and D.L. Dowe. MML estimation of the von Mises concentration parameter. Technical report TR 93/193, Dept. of Computer Science, Monash University, Clayton, Victoria 3168, Australia, 1993. prov. accepted, Aust. J. Stat.Google Scholar
  28. 28.
    C.S. Wallace and D.L. Dowe. Estimation of the von Mises concentration parameter using Minimum Message Length. In Proc. 12th Australian Statistical Soc. Conf., Monash University, Australia, 1994.Google Scholar
  29. 29.
    C.S. Wallace and D.L. Dowe. Intrinsic classification by MML — the Snob program. In C. Zhang, J. Debenham, and D. Lukose, editors, Proc. 7th Australian Joint Conf. on Artificial Intelligence, pages 37–44. World Scientific, Singapore, 1994. See ftp://ftp.cs.monash.edu.au/pub/snob/Snob.readme.Google Scholar
  30. 30.
    C.S. Wallace and D.L. Dowe. MML mixture modelling of Multi-state, Poisson, von Mises circular and Gaussian distributions. In Proc. Sydney International Statistical Congess (SISC-96), page 197, Sydney, Australia, 1996.Google Scholar
  31. 31.
    C.S. Wallace and P.R. Freeman. Estimation and inference by compact coding. Journal of the Royal Statistical Society (Series B), 49:240–252, 1987.Google Scholar
  32. 32.
    G.S. Watson and E.J. Williams. On the construction of significance tests on the circle and the sphere. Biometrika, 43:344–352, 1956.Google Scholar
  33. 33.
    S. Wolfram. Mathematical A System for Doing Mathematics by Computer. Addison-Wesley, Reading, Massachusetts, 1988.Google Scholar

Copyright information

© Springer-Verlag 1996

Authors and Affiliations

  • David L. Dowe
    • 1
  • Jonathan J. Oliver
    • 1
  • Chris S. Wallace
    • 1
  1. 1.Department of Computer ScienceMonash UniversityClaytonAustralia

Personalised recommendations