ANALYSIS OF CUMULANT COEFFICIENTS OF TWO-COMPONENT MIXTURES OF SHIFTED NON-GAUSSIAN DISTRIBUTIONS

A.I. Krasilnikov

Èlektron. model. 2021, 43(5):73-92
https://doi.org/10.15407/emodel.43.05.073

ABSTRACT

The dependence of the cumulant coefficients of two-component mixtures of shifted non-Gaussian distributions on the weight coefficient is analyzed and conditions are determined under which the cumulant coefficients of any orders are equal to zero. The dependence of the cumulant coefficients of two-component mixtures on the shear parameter is investigated and the parameter values are determined at which the cumulant coefficients of any orders have ext­rema and zeros. The dependence of the skewness and excess kurtosis of a two-component mixture of shifted Gumbel distributions of type 1 on the weight coefficient and the shear parameter is investigated and their values are obtained at which the skewness and excess kurtosis of the mixture are equal to zero. The features of computer modeling of random variables, the probability density of which is a two-component mixture of shifted distributions, are considered.

KEYWORDS

non-Gaussian distributions, two-component mixtures of distributions, cumulant analysis, cumulant coefficients, asymmetry coefficient, excess coefficient.

REFERENCES

  1. McLachlan, G. and Peel, D. (2000), Finite mixture models, John Wiley&Sons, New York, USA.
    https://doi.org/10.1002/0471721182
  2. Chauveau, D., Garel, B. and Mercier, S. (2019), “Testing for univariate two-component Gaussian mixture in practice”, Journal de la société française de statistique, Vol. 160, no. 1, 86-113.
  3. Kalantan, Z.I. and Alrewely, F. (2019), “A 2-Component Laplace Mixture Model: Properties and Parametric Estimations”, Mathematics and Statistics, Vol. 7, no. 4A, pp. 9-16. DOI: 10.13189/ms.2019.
    https://doi.org/10.13189/ms.2019.070702
  4. Sindhu, T.N., Feroze, N. and Aslam, M. (2014), “Bayesian Estimation of the Parameters of Two-Component Mixture of Rayleigh Distribution under Doubly Censoring”, Journal of Modern Applied Statistical Methods, Vol. 13, no. 2, pp. 259-286.
    https://doi.org/10.22237/jmasm/1414815180
  5. Evin, G., Merleau, J. and Perreault, L. (2011), “Two-component mixtures of normal, gamma, and Gumbel distributions for hydrological applications”, Water Resources Research, Vol. 47, no. 8, p. 1-21.
    https://doi.org/10.1029/2010WR010266
  6. Uma Maheswari, R. and Leo Alexander, T. (2017), “Mixture of identical distributions of exponential, gamma, lognormal, weibull, gompertz approach to heterogeneous survival data”, International Journal of Current Research, Vol. 9, 9, pp. 57521-57532.
  7. Shin, J.-Y., Lee, T. and Ouarda, T.B.M.J. (2015), “Heterogeneous Mixture Distributions for Modeling Multisource Extreme Rainfalls”, Journal of hydrometeorology, Vol. 16, no. 6, pp. 2639-2657.
    https://doi.org/10.1175/JHM-D-14-0130.1
  8. Türkan, A.H. and Çalış, N. (2014), “Comparison of two-component mixture distribution models for heterogeneous survival datasets: a review study”, ISTATISTIK: Journal of the Turkish Statistical Association, Vol. 7, no. 2, pp. 33-42.
  9. Uma Maheswari, R. and Leo Alexander, T. (2017), “Two-component of Non-Identical Mixture Distribution Models for heterogeneous Survival Data”, International Journal of Recent Scientific Research, Vol. 8, 10, pp. 20813-20824. DOI: http://dx.doi.org/10.24327/ijrsr.2017.0810.0965.
  10. Krasilnikov, A.I. and Pilipenko, K.P. (2008), “Application of a two-component Gaussian mixture to identify single-peak symmetric probability density functions”, Elektronika i sviaz, Vol. 5, no. 46, pp. 20-29.
  11. Krasilnikov, A.I. (2017), “Analysis of the kurtosis coefficient of contaminated gaussian distributions”, Elektronnoe modelirovanie, Vol. 39, no. 4, pp. 19-30.
    https://doi.org/10.15407/emodel.39.04.019
  12. Krasilnikov, A.I. (2020), “Analysis of cumulant coefficients of two-component mixtures of shifted gaussian distributions with equal variances”, Elektronnoe modelirovanie, Vol. 42, no. 3, pp. 71-88. DOI: https://doi.org/10.15407/emodel.42.03.071
  13. Chepynoha, A.V. (2010), “Areas of realization of bi-Gaussian models of skewness-excess random variables with the punched moment-cumulant description”, Visnyk ChDTU, Vol. 2, pp. 91-95.
  14. Sulewski, P. (2021), “Two-piece power normal distribution”, Communications in Statistics - Theory and Methods, Vol. 50, no. 11, pp. 2619-2639.
    https://doi.org/10.1080/03610926.2019.1674871
  15. Krasilnikov, A.I. (2013), “Class non-Gaussian distributions with zero skewness and kurtosis”, Radioelectronics and Communications Systems, Vol. 56, no. 6, pp. 312-320.
    https://doi.org/10.3103/S0735272713060071
  16. Krasilnikov, A.I. (2017), “Class of non-gaussian symmetric distributions with zero coefficient of kurtosis”, Elektronnoe modelirovanie, Vol. 39, no. 1, pp. 3-17.
    https://doi.org/10.15407/emodel.39.01.003
  17. Krasilnikov, A.I. (2016), “Models of asymmetrical distributions of random variables with zero asymmetry coefficient”, Elektronnoe modelirovanie, Vol. 38, no. 1, pp. 19-33.
    https://doi.org/10.15407/emodel.38.01.019
  18. Kunchenko, Yu.P., Zabolotnii, S.V., Koval, V.V. and Chepynoha, A.V. (2005), “Simulation of excess random variables with given cumulative description based on bi-Gaussian distribution”, Visnyk ChDTU, Vol. 1, pp. 38-42.
  19. Rubio, F.J., Ogundimu, E.O. and Hutton, J.L. (2016), “On modelling asymmetric data using two-piece sinh-arcsinh distributions”, Brazilian Journal of Probability and Statistics, Vol. 30, no. 3, pp. 485–501.
    https://doi.org/10.1214/15-BJPS290
  20. Krasilnikov, A.I. (2018), “The application of two-component mixtures of shifted distributions for modeling perforated random variables”, Elektronnoe modelirovanie, Vol. 40, no. 6, pp. 83-98.
    https://doi.org/10.15407/emodel.40.06.083
  21. Krasilnikov, A.I. (2018), “Modeling of perforated random variables on the basis of mixtures of shifted distributions”, Elektronnoe modelirovanie, Vol. 40, no. 1, pp 47-61.
    https://doi.org/10.15407/emodel.40.01.047
  22. Vadzinskii, R.N. (2001), Spravochnik po veroiatnostnym raspredeleniiam [Directory on Probabilistic Distributions], Nauka, St. Petersburg, Russia.

Full text: PDF