Research Article
BibTex RIS Cite

İKİ PARAMETRELİ RAYLEIGH DAĞILIMLARININ SONLU KARMALARINDA PARAMETRE TAHMİNİ

Year 2018, 18. EYI Special Issue, 383 - 398, 18.01.2018
https://doi.org/10.18092/ulikidince.352176

Abstract

Heterojen yapıda bir
popülasyondan elde edilmiş verilerin istatistiksel analizinde oldukça
kullanışlı modeller olan sonlu karma dağılımlar için parametre tahmin problemi
istatistikte oldukça önemli bir problemdir. Bu çalışma, iki parametreli
Rayleigh dağılımlarının sonlu karmaları için parametre tahmin problemini ele
almaktadır. Bu kapsamda, iki parametreli Rayleigh dağılımlarının sonlu
karmalarında mevcut bilinmeyen parametreler için en çok olabilirlik tahmin
edicileri E-M algoritmasına göre elde edilmektedir. Bununla birlikte çalışmada,
elde edilen en çok olabilirlik tahmin edicilerinin karma dağılımın bilinmeyen parametrelerini
tahmin etmedeki performansını ortaya koymak için, karma oran parametresinin ve
karma bileşen dağılımlarındaki parametrelerin farklı değerlerini göz önünde
bulunduran ve tahmin edicilere ait hata kareler ortalamalarını, yanlılık
miktarlarını ve standart sapmalarını ortaya koyan simülasyon çalışması
sonuçlarına yer verilmektedir. Buna ek olarak, açıklayıcı amaçlar için gerçek
bir veri seti kullanılarak yapılan bir de örneğe yer verilmektedir.

References

  • Açıkgöz, İ. (2007). Sonlu Karma Dağılımlarda Parametre Tahmini. (Yayımlanmamış Doktora Tezi). Ankara Üniversitesi Fen Bilimleri Enstitüsü, Ankara.
  • Afify, W. M. (2011). Classıcal Estimation of Mixed Rayleigh Distribution in Type I Progressive Cen-sored. Journal of Statistical Theory and Applications, 10(4), 619-632.
  • Dempster, A. P., Laird, N. M., ve Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the royal statistical society. Series B (methodological), 39(1), 1-38.
  • Dey, S., Dey, T. ve Kundu, D. (2014). Two-parameter Rayleigh distribution: different methods of estimation. American Journal of Mathematical and Management Sciences, 33(1), 55-74.
  • Dick, N. P. ve Bowden, D. C. (1973). Maximum likelihood estimation for mixtures of two normal distributions. Biometrics, 29(4), 781-790.
  • Elmahdy, E. E. ve Aboutahoun, A. W. (2013). A New Approach for Parameter Estimation of Finite Weibull Mixture Distributions for Reliability Modeling. Applied Mathematical Modelling, 37(4), 1800-1810.
  • Everitt, B. S. ve Hand, D. J. (1981). Finite Mixture Distributions. London: Monographs on Applied Probability and Statistics. Chapman and Hall.
  • Gupta, R. D. ve Kundu, D. (2003). Discriminating Between Weibull and Generalized Exponential Distributions. Computational statistics & data analysis, 43(2), 179-196.
  • Leytham, K. M. (1984). Maximum likelihood estimates for the parameters of mixture distributions. Water resources research, 20(7), 896-902.
  • Liu, Z., Almhana, J., Choulakian, V. ve McGorman, R. (2006). Traffic modeling with gamma mixtures and dynamical bandwidth provisioning. Communication Networks and Services Research Conference, 123-130, Canada.
  • McLachlan, G. J. ve Krishnan, T. (1997). The EM Algorithm and Extensions, (2nd ed.). Canada: Wiley series in probability and statistics.
  • Pearson, K. (1894). Contributions to the mathematical theory of evolution. Philosophical Transac-tions of the Royal Society of London. 185(A), 71-110.
  • Proschan, F. (1963). Theoretical Explanation of Observed Decreasing Failure Rate. Technometrics, 5(3), 375-383.
  • Sum, S. T. ve Oommen, B. J. (1995). Mixture decomposition for distributions from the exponential family using a generalized method of moments. IEEE transactions on systems, man, and cybernetics, 25(7), 1139-1149.
  • Wang, Y. ve Wang, J. (2014). The EM Algorithm for The Finite Mixture of Exponential Distribution Models. Int. J. Contemp. Math. Sciences, 9(2), 57-64.

PARAMETER ESTIMATION IN FINITE MIXTURES OF TWO-PARAMETER RAYLEIGH DISTRIBUTIONS

Year 2018, 18. EYI Special Issue, 383 - 398, 18.01.2018
https://doi.org/10.18092/ulikidince.352176

Abstract

The problem of parameter
estimation for finite mixture distributions, which are very useful models for
the statistical analysis of data obtained from a heterogeneous population, is
quite important problem in statistics. This paper focuses on the parameter
estimation problem for finite mixtures of the two-parameter Rayleigh
distributions. In this context, the maximum likelihood estimators for the
unknown parameters in the finite mixtures of the two-parameter Rayleigh
distributions are obtained according to the E-M algorithm. Furthermore, in
order to demonstrate the estimation performance of the obtained maximum
likelihood estimators, a simulation study which gives the mean square error,
bias and standard deviations of the estimators, is carried out by considering
for different values of the mixing ratios and parameters of the component
distributions. Also, an actual data set is analysed for illustrative purposes.

References

  • Açıkgöz, İ. (2007). Sonlu Karma Dağılımlarda Parametre Tahmini. (Yayımlanmamış Doktora Tezi). Ankara Üniversitesi Fen Bilimleri Enstitüsü, Ankara.
  • Afify, W. M. (2011). Classıcal Estimation of Mixed Rayleigh Distribution in Type I Progressive Cen-sored. Journal of Statistical Theory and Applications, 10(4), 619-632.
  • Dempster, A. P., Laird, N. M., ve Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the royal statistical society. Series B (methodological), 39(1), 1-38.
  • Dey, S., Dey, T. ve Kundu, D. (2014). Two-parameter Rayleigh distribution: different methods of estimation. American Journal of Mathematical and Management Sciences, 33(1), 55-74.
  • Dick, N. P. ve Bowden, D. C. (1973). Maximum likelihood estimation for mixtures of two normal distributions. Biometrics, 29(4), 781-790.
  • Elmahdy, E. E. ve Aboutahoun, A. W. (2013). A New Approach for Parameter Estimation of Finite Weibull Mixture Distributions for Reliability Modeling. Applied Mathematical Modelling, 37(4), 1800-1810.
  • Everitt, B. S. ve Hand, D. J. (1981). Finite Mixture Distributions. London: Monographs on Applied Probability and Statistics. Chapman and Hall.
  • Gupta, R. D. ve Kundu, D. (2003). Discriminating Between Weibull and Generalized Exponential Distributions. Computational statistics & data analysis, 43(2), 179-196.
  • Leytham, K. M. (1984). Maximum likelihood estimates for the parameters of mixture distributions. Water resources research, 20(7), 896-902.
  • Liu, Z., Almhana, J., Choulakian, V. ve McGorman, R. (2006). Traffic modeling with gamma mixtures and dynamical bandwidth provisioning. Communication Networks and Services Research Conference, 123-130, Canada.
  • McLachlan, G. J. ve Krishnan, T. (1997). The EM Algorithm and Extensions, (2nd ed.). Canada: Wiley series in probability and statistics.
  • Pearson, K. (1894). Contributions to the mathematical theory of evolution. Philosophical Transac-tions of the Royal Society of London. 185(A), 71-110.
  • Proschan, F. (1963). Theoretical Explanation of Observed Decreasing Failure Rate. Technometrics, 5(3), 375-383.
  • Sum, S. T. ve Oommen, B. J. (1995). Mixture decomposition for distributions from the exponential family using a generalized method of moments. IEEE transactions on systems, man, and cybernetics, 25(7), 1139-1149.
  • Wang, Y. ve Wang, J. (2014). The EM Algorithm for The Finite Mixture of Exponential Distribution Models. Int. J. Contemp. Math. Sciences, 9(2), 57-64.
There are 15 citations in total.

Details

Journal Section Articles
Authors

Hayrinisa Demirci Biçer

Cenker Biçer

Publication Date January 18, 2018
Published in Issue Year 2018 18. EYI Special Issue

Cite

APA Demirci Biçer, H., & Biçer, C. (2018). İKİ PARAMETRELİ RAYLEIGH DAĞILIMLARININ SONLU KARMALARINDA PARAMETRE TAHMİNİ. Uluslararası İktisadi Ve İdari İncelemeler Dergisi383-398. https://doi.org/10.18092/ulikidince.352176

______________________________________________________

Address: Karadeniz Technical University Department of Economics Room Number 213  

61080 Trabzon / Turkey

e-mail : uiiidergisi@gmail.com