Advertisement

An Efficient Brute Force Approach to Fit Finite Mixture Distributions

  • Falko BauseEmail author
Conference paper
  • 83 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12040)

Abstract

This paper presents a brute force approach to fit finite mixtures of distributions considering the empirical probability density and cumulative distribution functions as well as the empirical moments. The fitting problem is solved using a non-negative least squares method determining a mixture from a larger set of distributions.

The approach is experimentally validated for finite mixtures of Erlang distributions. The results show that a feasible number of component distributions, which accurately fit to the empirical data, is obtained within a short CPU time.

Keywords

Mixture distributions Hyper-Erlang distributions Non-negative least squares Farey sequences 

References

  1. 1.
    Akaike, H.: A new look at the statistical model identification. IEEE Trans. Autom. Control 19(6), 716–723 (1974)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Asmussen, S., Nerman, O., Olsson, M.: Fitting phase-type distributions via the EM algorithm. Scand. J. Stat. 23(4), 419–441 (1996)zbMATHGoogle Scholar
  3. 3.
    Bause, F., Buchholz, P., Kriege, J.: ProFiDo - the processes fitting toolkit Dortmund. In: Proceedings of the 7th International Conference on Quantitative Evaluation of SysTems (QEST 2010), pp. 87–96. IEEE Computer Society (2010)Google Scholar
  4. 4.
    Bause, F., Horvath, G.: Fitting Markovian arrival processes by incorporating correlation into phase type renewal processes. In: Proceedings of the 2010 Seventh International Conference on the Quantitative Evaluation of Systems, QEST 2010, pp. 97–106. IEEE Computer Society, Washington, DC, USA (2010)Google Scholar
  5. 5.
    Bobbio, A., Horváth, A., Telek, M.: Matching three moments with minimal acyclic phase type distributions. Stoch. Models 21(2–3), 303–326 (2005)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Bobbio, A., Telek, M.: A benchmark for PH estimation algorithms: results for acyclic-PH. Commun. Stat. Stoch. Models 10(3), 661–677 (1994)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Buchholz, P., Felko, I., Kriege, J.: Transformation of acyclic phase type distributions for correlation fitting. In: Dudin, A., De Turck, K. (eds.) ASMTA 2013. LNCS, vol. 7984, pp. 96–111. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-39408-9_8CrossRefGoogle Scholar
  8. 8.
    Buchholz, P., Kriege, J.: A heuristic approach for fitting MAPs to moments and joint moments. In: Proceedings of the 6th International Conference on Quantitative Evaluation of SysTems (QEST 2009), pp. 53–62. IEEE Computer Society, Los Alamitos, CA, USA, (2009)Google Scholar
  9. 9.
    Buchholz, P., Kriege, J., Felko, I.: Input Modeling with Phase-Type Distributions and Markov Models - Theory and Applications. SpringerBriefs in Mathematics. Springer, Heidelberg (2014).  https://doi.org/10.1007/978-3-319-06674-5CrossRefzbMATHGoogle Scholar
  10. 10.
    Buchholz, P., Telek, M.: Stochastic Petri nets with matrix exponentially distributed firing times. Perform. Eval. 67(12), 1373–1385 (2010)CrossRefGoogle Scholar
  11. 11.
    David, A., Larry, S.: The least variable phase type distribution is Erlang. Commun. Stat. Stoch. Models 3(3), 467–473 (1987)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Fang, Y.: Hyper-Erlang distribution model and its applications in wireless mobile networks. Wirel. Netw. 7, 211–219 (2001)CrossRefGoogle Scholar
  13. 13.
    Freedman, D., Diaconis, P.: On the histogram as a density estimator: \(L_2\) theory. Zeitschrift für Wahrscheinlichkeitstheorie und Verwandte Gebiete 57(4), 453–476 (1981)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Frühwirth-Schnatter, S.: Finite Mixture and Markov Switching Models. Springer Series in Statistics. Springer, New York (2006).  https://doi.org/10.1007/978-0-387-35768-3CrossRefzbMATHGoogle Scholar
  15. 15.
    Frühwirth-Schnatter, S., Celeux, G., Robert, C.: Handbook of Mixture Analysis. Chapman & Hall/CRC Handbooks of Modern Statistical Methods. CRC Press, Taylor & Francis Group, Boca Raton (2019)CrossRefGoogle Scholar
  16. 16.
    Hardy, G., Wright, E.: An Introduction to the Theory of Numbers, 5th edn. Oxford Science Publications. Clarendon Press, Oxford (1979)Google Scholar
  17. 17.
    Horváth, A., Telek, M.: Markovian modeling of real data traffic: heuristic phase type and MAP fitting of heavy tailed and fractal like samples. In: Calzarossa, M.C., Tucci, S. (eds.) Performance 2002. LNCS, vol. 2459, pp. 405–434. Springer, Heidelberg (2002).  https://doi.org/10.1007/3-540-45798-4_17CrossRefzbMATHGoogle Scholar
  18. 18.
    Horváth, G.: Moment matching-based distribution fitting with generalized hyper-Erlang distributions. In: Dudin, A., De Turck, K. (eds.) ASMTA 2013. LNCS, vol. 7984, pp. 232–246. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-39408-9_17CrossRefGoogle Scholar
  19. 19.
    Horváth, G., Telek, M.: On the canonical representation of phase type distributions. Perform. Eval. 66(8), 396–409 (2009). Selected Papers of the Fourth European Performance Engineering Workshop (EPEW) 2007 in BerlinCrossRefGoogle Scholar
  20. 20.
    Internet Traffic Archive. ftp://ita.ee.lbl.gov/html/traces.html. Accessed: 13 Nov 2019Google Scholar
  21. 21.
    Johnson, M.A., Taaffe, M.R.: Matching moments to phase distributions: mixtures of Erlang distributions of common order. Commun. Stat. Stoch. Models 5(4), 711–743 (1989)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Khayari, R.E.A., Sadre, R., Haverkort, B.R.: Fitting world-wide web request traces with the EM-algorithm. Perform. Eval. 52(2–3), 175–191 (2003)CrossRefGoogle Scholar
  23. 23.
    Lawson, C., Hanson, R.: Solving Least Squares Problems. Society for Industrial and Applied Mathematics. SIAM, New Delhi (1995)Google Scholar
  24. 24.
    Neuts, M.: A versatile Markovian point process. J. Appl. Probab. 16(4), 764–779 (1979)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Neuts, M.: Matrix-Geometric Solutions in Stochastic Models: An Algorithmic Approach. Johns Hopkins Series in the Mathematical Sciences. Johns Hopkins University Press, Baltimore (1981)Google Scholar
  26. 26.
    O’Cinneide, C.A.: Phase-type distributions: open problems and a few properties. Commun. Stat. Stoch. Models 15(4), 731–757 (1999)MathSciNetCrossRefGoogle Scholar
  27. 27.
    Okamura, H., Dohi, T., Trivedi, K.S.: A refined EM algorithm for PH distributions. Perform. Eval. 68(10), 938–954 (2011)CrossRefGoogle Scholar
  28. 28.
    Panchenko, A., Thümmler, A.: Efficient phase-type fitting with aggregated traffic traces. Perform. Eval. 64(7–8), 629–645 (2007)CrossRefGoogle Scholar
  29. 29.
    Reinecke, P., Krauß, T., Wolter, K.: Cluster-based fitting of phase-type distributions to empirical data. Comput. Math. Appl. Theory Pract. Stoch. Model. 64(12), 3840–3851 (2012)MathSciNetzbMATHGoogle Scholar
  30. 30.
    Reinecke, P., Krauß, T., Wolter, K.: Phase-type fitting using HyperStar. In: Balsamo, M.S., Knottenbelt, W.J., Marin, A. (eds.) EPEW 2013. LNCS, vol. 8168, pp. 164–175. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-40725-3_13CrossRefGoogle Scholar
  31. 31.
    Telek, M., Horvath, G.: A minimal representation of Markov arrival processes and a moments matching method. Perform. Eval. 64(9–12), 1153–1168 (2007)CrossRefGoogle Scholar
  32. 32.
    Thümmler, A., Buchholz, P., Telek, M.: A novel approach for fitting probability distributions to real trace data with the EM algorithm. In: Proceedings of the International Conference on Dependable Systems and Networks, DSN 2005, pp. 712–721, June 2005 (2005)Google Scholar
  33. 33.
    Titterington, D.M., Smith, A.F.M., Makov, U.E.: Statistical Analysis of Finite Mixture Distributions. Wiley, Hoboken (1985)zbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.LS Informatik IV, Department of Computer ScienceTU DortmundDortmundGermany

Personalised recommendations