A Mixture Model of Two Bivariate Weibull Distributions

Year 2018, Volume: 31 Issue: 2, 643 - 658, 01.06.2018

Ayça Hatice Türkan Nazif Çalış

Abstract

In this paper, we propose a mixture model containing bivariate
Weibull distributions—the Marshall-Olkin bivariate Weibull (MOBW) and the Block-Basu
bivariate Weibull (BBBW)—because each of these distributions alone is
inadequate for explaining a data set when certain special situations occur in
bivariate lifetime data sets. We refer to the proposed model as Mix_BW. To estimate
the model parameters, we use the expectation-maximisation (EM) algorithm in an
adapted form we term the Mix_EM algorithm. We provide illustrative examples
with real and simulated data sets to demonstrate the applicability of the
proposed Mix_BW model.

Keywords

Block-Basu bivariate Weibull (BBBW), Marshall-Olkin bivariate Weibull (MOBW), Maximum Likelihood Estimation, Mixture distribution model

References

• Funda Erdugan Kırıkkale University [e-mail]
• Murat Erişoğlu Necmettin Erbakan University [e-mail]
• Tayfun Servi Adıyaman University [e-mail]