Methodology and Computing in Applied Probability

, Volume 17, Issue 3, pp 541–564 | Cite as

Moments and Cumulants of a Mixture

  • Christopher S. Withers
  • Saralees Nadarajah
  • Shou Hsing Shih
Article
  • 271 Downloads

Abstract

For the first time, general formulas for moments and cumulants are derived for mixtures of two or more distributions. The formulas involve the Bell polynomials. Computational efficiency of the formulas is illustrated by applications for two-component and three-component normal mixture models.

Keywords

Bell polynomials CPU time Cumulants Mixtures Moments 

AMS 2000 Subject Classification

62F03 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Andrews DF (2001) Asymptotic expansions of moments and cumulants. Stat Comput 11:7–16MathSciNetCrossRefGoogle Scholar
  2. Andrews DF, Stafford JE (2000) Symbolic computation for statistical inference. Oxford University Press, OxfordMATHGoogle Scholar
  3. Bosdogianni P, Petrou M, Kittler J (1997) Mixture models with higher order moments. IEEE Trans Geosci Remote Sens 35:341–353CrossRefGoogle Scholar
  4. Comtet L (1974) Advanced combinatorics. Reidel Publishing Company, DordrechtCrossRefMATHGoogle Scholar
  5. Cornell JA (1981) Experiments with mixtures: designs, models, and the analysis of mixture data. Wiley, New YorkMATHGoogle Scholar
  6. Cubarsi R (1992) Central moments of the velocity distribution from a superposition of two stellar systems. Astrophys J 103:1608–1620Google Scholar
  7. Cubarsi R, Alcobé S (2004) Cumulants and symmetries in a trivariate normal mixture: a qualitative study of the local velocity distribution. Astron Astrophys 427:131–144CrossRefGoogle Scholar
  8. Di Nardo E, Guarino G, Senato D (2008) Symbolic computation of moments of sampling distributions. Comput Stat Data Anal 52:4909–4922CrossRefMATHGoogle Scholar
  9. Douglas JB (1980) Analysis with standard contagious distributions. International Co-operative Publishing House, Fairland, MarylandMATHGoogle Scholar
  10. Everitt BS, Hand DJ (1981) Finite mixture distributions. Chapman and Hall, LondonCrossRefMATHGoogle Scholar
  11. Gini F (1997) A cumulant based adaptive technique for coherent radar detection in a mixture of K-distributed clutter and Gaussian disturbance. IEEE Trans Signal Process 45:1507–1519CrossRefMATHGoogle Scholar
  12. Jacobs PA, Lewis PAW (1983) Stationary discrete autoregressive-moving average time series generated by mixtures. J Time Ser Anal 4:19–36MathSciNetCrossRefMATHGoogle Scholar
  13. Kontorovich V (2007) Applied statistical analysis for strange attractors and related problems. Mathematical Methods in Applied Science 30:1705–1717MathSciNetCrossRefMATHGoogle Scholar
  14. MathWorks Inc. (2010) Matlab, Version 7.10.0. Natick, MassachusettsGoogle Scholar
  15. McCullagh P (1987) Tensor methods in statistics. Chapman and Hall, LondonMATHGoogle Scholar
  16. McLachlan GJ, Basford KE (1988) Mixture models: inference and applications to clustering. Marcel Dekker, New YorkMATHGoogle Scholar
  17. McLachlan GJ, Peel D (2000) Finite mixture models. Wiley, New YorkCrossRefMATHGoogle Scholar
  18. Noam Y, Tabrikian J (2005) Parametric estimation of cumulants. In: Proceedings of the international conference on acoustics speech and signal processing, pp 305–308Google Scholar
  19. Perez-Quiros G, Timmermann A (2001) Business cycle asymmetries in stock returns: evidence from higher order moments and conditional densities. J Econ 103:259–306MathSciNetCrossRefMATHGoogle Scholar
  20. Pokharel PP, Liu WF, Principe JC (2009) A low complexity robust detector in impulsive noise. Signal Process 89:1902–1909CrossRefMATHGoogle Scholar
  21. Poloskov IE (2003) CAS mathematica in random studies. Lect Notes Comput Sci 2657:781–790MathSciNetCrossRefGoogle Scholar
  22. Primak S, Kontorovich V, Lyandres V (2004) Stochastic methods and their applications to communications: stochastic differential equations approach. Wiley, ChichesterCrossRefGoogle Scholar
  23. Stuart A, Ord K (1987) Kendall’s advanced theory of statistics, vol 1, 5th edn. Griffin, LondonGoogle Scholar
  24. Taylor DH (1965) Latency models for reaction time distributions. Psychometrika 30:157–163CrossRefGoogle Scholar
  25. Titterington DM, Smith AFM, Makov UE (1985) Statistical analysis of finite mixture distributions. Wiley, ChichesterMATHGoogle Scholar
  26. Wang J, Huang DX, Yuan XH (2008) A cumulant-based adaptive detection technique for optical wireless communication over strong turbulence channels. China Communications 5:22–27Google Scholar
  27. Weiß CH, Göb R (2008) Measuring serial dependence in categorical time series. Advances in Statistical Analysis 92, 71–89CrossRefMATHGoogle Scholar
  28. Withers CS, Nadarajah S (2008) Multivariate Bell polynomials and their applications to powers and fractionary iterates of vector power series and to partial derivatives of composite vector functions. Appl Math Comput 206:997–1004MathSciNetCrossRefMATHGoogle Scholar
  29. Withers CS, Nadarajah S (2010) Multivariate Bell polynomials, series, chain rules, moments and inversion. Utilitas Mathematica 83:133–140MathSciNetMATHGoogle Scholar
  30. Wolfram Research, Inc.: Mathematica, Version 8.0. Champaign, Illinois (2010)Google Scholar
  31. Zheng Q (2002) Computing relations between moments and cumulants. Comput Stat 17:507–515CrossRefMATHGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Christopher S. Withers
    • 1
  • Saralees Nadarajah
    • 2
  • Shou Hsing Shih
    • 3
  1. 1.Applied Mathematics GroupIndustrial Research LimitedLower HuttNew Zealand
  2. 2.School of MathematicsUniversity of ManchesterManchesterUK
  3. 3.Department of Mathematics and StatisticsAmerican University of SharjahSharjahUAE

Personalised recommendations