A representation of random variables for finite mixture model based on combinatorial form

Authors

  • Supawan Khotama
  • Watcharin Klongdee

Keywords:

Mixture model, Random variable, mixing weight, Generating

Abstract

A formula of generating random variable for finite mixture model is proposed. The main contribution of the work is a representation of random variable for finite cdf mixture model. We illustrate the generating random variable from the four components including a mixture of normal distribution, logistic distribution, log-normal distribution and gamma distribution in case of the number of the random variable is different, which present both the density and the cumulative probability and compare with mixture distribution. The results show that the more numbers of the random variable, the more the density and the cumulative probability are at the similar values more than small amount of number of the random variable.

Author Biographies

Supawan Khotama

Mathematics Department, Khon Kaen University

Watcharin Klongdee

Mathematics Department, Khon Kaen University

References

[1] Farnoosh R, Zarpak B. Image segmentation using Gaussian mixture model. IUST International Journal of Engineering Science. 2008; 19(1-2): 29-32.

[2] Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning. 2nd ed.
California: Springer; 2008.

[3] Kollu R, Rayapudi SR, Narasimham SVL, Pakkurthi KM. Mixture probability distribution functions to model wind speed distributions. International Journal of Energy and Environmental Engineering. 2012; 3-27.

[4] Mikosch T. Non-Life Insurance Mathematics. 2nd ed. Berlin: Springer; 2008.

[5] Morgan EC, Lackner M, Vogel RM, Baise LG. Probability distribution for offshore wind speeds. Energy Conversion and Management. 2011; 52(2011): 15-26.

[6] Seydel R. Tools for Computation Finance. 2nd ed. Berlin: Springer; 2003.

Downloads

Published

2018-06-30

How to Cite

Khotama, S., & Klongdee, W. (2018). A representation of random variables for finite mixture model based on combinatorial form. Journal of Applied Statistics and Information Technology, 3(1), 25–31. Retrieved from https://ph02.tci-thaijo.org/index.php/asit-journal/article/view/166882