Bayesian Estimation of the Weibull Parameters Based on Competing Risks Grouped Data


Abstract


Based on the competing risks grouped data, Bayesian estimation approach is considered for the parameters of the Weibull distribution and the related specific hazard and survival functions. The estimation procedures are carried out under the square error loss (SELF) and linear exponential loss (LINEX) functions. High posterior (HPD) credible intervals for the specified parameters are also obtained. The derived estimators are in explicit closed forms. Their properties and performance are illustrated through an application to real lifetime’s data and an extended simulation study. Overall results indicate that, the Bayesian estimators are dominated other estimators obtained by other methods and are recommended when continuous life testing is not available.

DOI Code: 10.1285/i20705948v11n2p687

Keywords: Weibull distribution; competing risks; grouped data; loss function; HPD credible interval.

References


Al-Salem, M., Almomani, M., Alrefaei, M., and Diabat, A. (2017). On the optimal computing budget allocation problem for large scale simulation optimization. Simulation Modelling Practice and Theory, 71:149–159.

Almomani, M. and Alrefaei, M. (2012). A three-stage procedure for selecting a good enough simulated system. Journal of Applied Probability and Statistics, 6(1&2):13–27. Almomani, M. and Alrefaei, M. (2016). Ordinal optimization with computing budget allocation for selecting an optimal subset. Asia-Pacific Journal of Operational Research, 33(2). Almomani, M., Alrefaei, M., and Mansour, S. A. (2017). A combined statistical selection procedure measured by expected opportunity cost. Arabian Journal for Science and Engineering. Almomani, M. and R.AbdulRahman (2012). Selecting a good stochastic system for the large number of alternatives. Communications in Statistics-Simulation and Computation, 41:222–237. Alrefaei, M. and Almomani, M. (2007). Subset selection of best simulated systems. Journal of the Franklin Institute, 344:495–506.

Aludaat, K., Alodat, M. T., and Alodat, T. (2008). Parameter estimation of burr type x distribution for grouped data. Applied Mathematical Sciences, 2(9):415–423. Alwasel, I. (2009). Statistical inference of a competing risks model with modified weibull distributions. International Journal of Math Analysis, 3:905–918. Berger, J. (1985). Statistical decision theory and Bayesian analysis. 2nd edition. Springer, New York. Chambers, J., Cleveland, W., Kleiner, B., and Tukey, P. (1983). Graphical Methods for Data Analysis. Wadsworth, California. David, H. and Moeschberger, M. (1978). The Theory of Competing Risks. Charles Griffn & Company, London. Dey, A., Jha, A., and Dey, S. (2016). Bayesian analysis of modified weibull distribution under progressively censored competing risk model. In arXiv preprint arXiv:1605.06585.

Gove, J. and Fairweather, S. (1989). Maximum likelihood estimation of weibull function parameters using a general interactive optimizer and grouped data. Forest Ecology and Management, 28(1):61–69. Hamada, M., Reese, C., Wilson, A., and Martz, H. (2008). Bayesian Reliability. Springer, New York ,NY,USA. Iskandar, I. and Gondokaryono, Y. (2016). Competing risk models in reliability systems, a weibull distribution model with bayesian analysis approach. In In IOP Conference Series: Materials Science and Engineering, volume 114, page 012064. Josmar, M. and Jorge, A. (2011). Lindley distribution applied to competing risks lifetime. Computer Methods and Programs in Biomedicine, 104:188–192. Lai, C. and Murthy, D. (2003). A modified weibull distribution. IEEE Transaction on Reliability, 52(1):33–37. Lai, X., Yau, K., and Liu, L. (2017). Competing risk model with bivariate random effectsfor clustered survival data. Computational Statistics & Data Analysis, 112:215–223. Lianfen, Q. and Jose, C. C. (2003). Estimation of the weibull parameters for grouped data with competing risks. Journal of Statistical Computation and Simulation, 73:261–275. Lowe, P. and Lewis, W. (1983). Reliability analysis based on weibull distribution: an application to maintenance float factors. International Journal of Production Research, 21(4):461–470. Migdadi, H. and Al-Batah, M. (2014). Bayesian inference based on the interval grouped data from the weibull model with application. British Journal of Mathematics & Computer Science, 4(9):1170–1183. Mudholkar, G. and Asubonteng, K. (2010). Data-transformation approach to lifetimes data analysis: An overview. Journal of Statistical Planning and Inference, 140(10):2904–2917. Pipper, C. and Ritz, C. (1989). Checking the grouped data version of the cox model forinterval-grouped survival data. Scandinavian Journal of Statistics, 34(2):405–418. Rinne, H. (2009). The Weibull Distribution. Chapman and Hall, USA. Sarhan, A. M. (2007). Analysis of incomplete censored data in competing risks models with generalized exponential distributions. IEEE Trans in Reliability, 56:132–138. Shai, Y. and Wu, M. (2016). Statistical analysis of dependent competing risks model from gompertz distribution under progressively hybrid censoring. Springer Plus, 5(1):1745. Varian, H. (1975). A bayesian approach to real estate assessment. Studies in Bayesian Econometric and Statistics in honor of Leonard J. Savage, pages 195–208. Weibull, W. (1951). A statistical distribution function of wide applicability. Journal of Applied Mechanics, 18:293–297. Yanez, S., Escobar, L., and Gonzalez, N. (2014). Characteristics of two competing risks models with weibull distributed risks. Revista de la Academia Colombiana de Ciencias Exactas, Fsicas y Naturales, 38(148):298–311.

Yazhou, J., Molin, W., and Zhixin, J. (1995). Probability distribution of machining center failures. Reliability Engineering and System Safety, 50(1):121–125. Zellner, A. (1986). Bayesian estimation and prediction using asymmetric loss functions. Journal of the American Statistical Association, 81(394):446–451.


Full Text: pdf
کاغذ a4

Creative Commons License
This work is licensed under a Creative Commons Attribuzione - Non commerciale - Non opere derivate 3.0 Italia License.