Comparison of improved class of priors for the analysis of the Burr type VII model under doubly censored samples

Year 2021, , 1509 - 1533, 15.10.2021

Navid Feroze Muhammad Aslam

https://doi.org/10.15672/hujms.989479

Cited By: 1

Abstract

In recent years, the finite mixture lifetime models have frequently been used in chemical, physical, social science, biological and other fields due to their methodological development and practical applications. The Bayesian analysis of the mixture models has also developed a significant interest among the statisticians especially in the last decade. However, the most of these contributions are limited to the Bayes estimation for the parameters of lifetime models under singly type I censoring. This paper discusses the Bayesian estimation for the two-component mixture of the lifetime models under doubly censored samples with a particular case for the Burr type VII model. A class of improved priors has been proposed for the posterior estimation. The likelihood function, for doubly censored samples using two-component mixture of life time distributions, has been introduced. The hazard rate function for the mixture model has been compared for different parametric values. The performance of various estimators has been compared under a simulation study along with a real life example.

Keywords

Mixture models, posterior distributions, loss functions, credible intervals, posterior predictive intervals

References

• [1] W.M. Afify, Classical estimation of mixed Rayleigh distribution in type I progressive censored, J. Stat. Theory Appl. 10 (4), 619-632, 2011.
• [2] K.E. Ahmad, H.M. Moustafa and A.M. Abd-El-Rahman, Approximate Bayes estimation for mixtures of two Weibull distributions under type II censoring, J. Stat. Comput. Simul. 58 (3), 267-285, 1997.
• [3] M. Aslam, An application of prior predictive distribution to elicit the prior density, J. Stat. Theory Appl. 2 (1), 183-197, 2003.
• [4] L.D. Brown, Inadmissibility of the usual estimators of scale parameters in problems with unknown location and scale parameters, Ann. Math. Statist. 39 (1), 29-48, 1968.
• [5] W.I. Burr, Cumulative frequency distribution, Ann. Math. Statist. 13 (2), 215-232, 1942.
• [6] K.M. Chaloner, T. Church, T.A. Louis and J.P. Matts, Graphical elicitation of a prior distribution for a clinical trial, Statistician 42, 341-353, 1993.
• [7] K.M. Chaloner and G.T. Duncan, Assessment of a Beta prior distribution: PM elicitation, Statistician 32, 174-180, 1983.
• [8] E. Demidenko, Mixed Models: Theory and Applications, Wiley, 2004.
• [9] U. Erisoglu, M. Erisoglu and H. Erol, A mixture model of two different distributions approach to the analysis of heterogeneous survival data, World Acad Sci Eng Technol 78 (2), 41-45, 2011.
• [10] N. Feroze and M. Aslam, On Bayesian analysis of Burr type VII distribution under different censoring schemes, Int. J. Qual. Reliab. Manag. 3, Doi:10.1155/2012/248146, 2012.
• [11] N. Feroze and M. Aslam, Bayesian analysis of Burr type X distribution under complete and censored samples, Int J Pure Appl Sci Technol 11 (2), 16-28, 2012.
• [12] N. Feroze and M. Aslam, Bayesian analysis of Gumbel type II distribution under doubly censored samples using different loss functions, Casp. J. Appl. Sci. Res. 1 (10), 1-10, 2012.
• [13] P.H. Garthwaite and J.M. Dickey, Elicitation of prior distributions for variableselection problems in regression, Ann. Statist. 20 (4), 1697-1719, 1992.
• [14] C.F. Gauss, Least Squares Method for the Combinations of Observations, Mallet- Bachelier, 1810.
• [15] E.A. Gehan, A generalized two-sample Wilcoxon test for doubly censored data, Biometrika 52 (3/4), 650-653, 1965.
• [16] S. Geisser, A Predictive Primer, Bayesian Analysis in Econometrics and Statistics, in: A. Zellner (ed.), Amsterdam: North-Holland, 1980.
• [17] A. Gelman, J.B. Carlin, H.S. Stern and D.B. Rubin, Bayesian Data Analysis, 2nd ed., Chapman and Hall/CRC, 2004.
• [18] A. Haq, New improved informative priors for variance of Normal distribution, Available at: http://interstat.statjournals.net/YEAR/2009/abstracts/0911003. php.
• [19] S.A. Ismail and I.H. El-Khodary, Characterization of mixtures of exponential family distributions through conditional expectation, in: Annual Conference on Statistics and Computer Modeling in Human and Social Sciences, 13, 64-73, 2001.
• [20] P.S. Laplace, Theorie Analytique Des Probabilities, Veuve Courcier, 1812.
• [21] J.F. Lawless, Statistical Models time Data, 2nd ed., Wiley, 2003.
• [22] A.M. Legendre, New Methods for the Determination of Orbits of Comets, Courcier, 1805.
• [23] B.G. Lindsay, Mixture Models: Theory, Geometry and Applications, The Institute of Mathematical Statistical, Hayward, CA, 1995.
• [24] G.J. Maclachlan and D. Peel, Finite Mixture Models, Wiley, 2000.
• [25] M.Y. Majeed and M. Aslam, Bayesian analysis of the two component mixture of inverted exponential distribution under quadratic loss functions, Int. J. Phys. Sci. 7 (9), 1424-1434, 2012.
• [26] C.E. Mcculloch and S.R. Searle, Generalized, Linear and Mixed Models, Wiley, 2001.
• [27] W. Mendenhall and R.J. Hadar, Estimation of Parameters of Mixed Exponential Distributions from Censored Life Test Data, John Wiley and Sons, 1958.
• [28] M.A.M. Mousa and Z.F. Jaheen, Statistical inference for the Burr model based on progressively censored data, Comput. Math. Appl. 43 (10-11), 1441-1449, 2002.
• [29] J.A. Nachlas and A. Kumar, Reliability estimation using doubly censored field data, IEEE Trans. Rel. 42 (2), 268-278, 1993.
• [30] M.T. Nair and E.S. Abdul, Finite mixture of exponential model and its applications to renewal and reliability theory, J. Stat. Theory Pract. 4 (3), 367-373, 2010.
• [31] M.M. Nassar, Two properties of mixtures of exponential distributions, IEEE Trans. Rel. 37 (4), 383-385, 1988.
• [32] M.M. Nassar and M.R. Mahmoud, On characterizations of a mixture of exponential distributions, IEEE Trans. Rel. 34 (5), 484-488, 1985.
• [33] H. Panahi and S. Asadi, Analysis of the type-II hybrid censored Burr type XII distribution under linex loss function, Appl. Math. Sci. 5 (79), 3929-3942, 2011.
• [34] P.G. Peer, J.A. Van Dijck, J.H. Hendriks and A.L. Verbeek, Age dependent growth data of primary breast cancer, Cancer 71 (11), 3547-3551, 1993.
• [35] M. Raqab and M. Madi, Bayesian prediction of the total time on test using doubly censored Rayleigh data, J. Stat. Comput. Simul. 72 (10), 781-789, 2002.
• [36] M. Saleem and M. Aslam, Bayesian analysis of the two component mixture of the Rayleigh dist. With the uniform and the Jeffreys priors, J. Appl. Stat. Sci. 16 (4), 105-113, 2008.
• [37] M. Saleem and M. Aslam, On prior selection for the mixture of Rayleigh distribution using predictive Intervals, Pak. J. Statist. 24 (1), 21-35, 2008.
• [38] M. Saleem, M. Aslam and P. Economou, On the Bayesian analysis of the mixture of power function distribution using the complete and the censored sample, J. Appl. Stat. 37 (1), 25-40, 2010.
• [39] M. Saleem and M. Irfan, On properties of the Bayes estimates of the Rayleigh mixture parameters: a simulation study, Pak. J. Statist. 26 (3), 547-555, 2010.
• [40] Q. Shao, Notes on maximum likelihood estimation for the three-parameter Burr XII distribution, Comput. Stat. Data Anal. 45 (3), 675-687, 2004.
• [41] Q. Shao, H. Wong and J. Xia, Models for extremes using the extended three parameter Burr XII system with application to flood frequency analysis, Hydrol. Sci. J. 49 (4), 685-702, 2004.
• [42] G.O. Silva, E.M. Ortega, V.G. Cancho and M.L. Barreto, Log-Burr XII regression models with censored data, Comput. Statist. Data Anal. 52 (7), 3820-3842, 2008.
• [43] A.A. Soliman, Reliability estimation in a generalized life model with application to the Burr-XII, IEEE Trans. Rel. 51 (3), 337-343, 2002.
• [44] A.A. Soliman, Estimation of parameters of life from progressively censored data using Burr-xii model, IEEE Trans. Rel. 54 (1), 34-42, 2005.
• [45] K.S. Sultan, M.A. Ismail and A.S. Al-Moisheer, Mixture of two inverse Weibull distributions: properties and estimation, Comput. Statist. Data Anal. 51 (11), 5377-5387, 2007.
• [46] J.G. Surles and W.J. Padgett, Inference for reliability and stress-length for a scaled Burr type x distribution, Lifetime Data Anal. 7 (2), 187-202, 2001.
• [47] D.M. Titterington, A.F.M. Smith and U.E. Makov, Statistical Analysis of Finite Mixture Distributions, Wiley, 1985.
• [48] B.W. Turnbull, Non-Parametric estimation of a survivorship function with doubly censored data, J. Amer. Statist. Assoc. 69 (345), 169-173, 1974.
• [49] A.S. Wahed, Bayesian inference using Burr model under asymmetric loss function: an application to carcinoma survival data, J. Statist. Res. 40 (1), 45-57, 2006.
• [50] S.J. Wu, Y.J. Chen and C.T. Chang, Statistical inference based on progressively censored samples with random removals from the Burr type xii distribution, J. Stat. Comput. Simul. 77 (1), 19-27, 2007.
• [51] J.W. Wu and H.Y. Yu, Statistical inference about the shape parameter of the Burr type xii distribution under the failure-censored sampling plan, Appl. Math. Comput. 163 (1), 443-482, 2005.