×

Bayesian modeling of bathtub shaped hazard rate using various Weibull extensions and related issues of model selection. (English) Zbl 1257.62030

Summary: The bathtub shape is one of the most important behaviors of hazard rate functions that is quite common in life time data analysis. Such shapes are actually the combination of three different shapes and, as such, there have been several proposals to model such behavior. One such proposal is to combine at most three different distributions, often the Weibull or some similar model, separately for decreasing, constant, and increasing shapes of the hazard rate. Sometimes combination of two different models may also result in the required bathtub shape. The other proposal includes generalizing or modifying the two-parameter distribution by adding an extra parameter to it. It is often seen that the first proposal is quite cumbersome whereas the second fails to capture some important aspects of the data.
The present work considers two recent generalizations/modifications of the two-parameter Weibull model, namely the Weibull extension and the modified Weibull models, and proposes mixing the two families separately with the three-parameter Weibull distribution in order to see if the mixing results in some real benefit though at the cost of too many parameters. The paper finally considers the complete Bayes analysis of the proposed models using Markov chain Monte Carlo simulations and compares them with both Weibull extensions and modified Weibull models in a Bayesian framework. It is observed that the mixture models offer drastic improvement over the individual models not only in terms of hazard rate but also in terms of overall performance. The results are illustrated with the help of a real data based example.

MSC:

62F15 Bayesian inference
62N03 Testing in survival analysis and censored data
62N05 Reliability and life testing
65C40 Numerical analysis or methods applied to Markov chains
62A09 Graphical methods in statistics
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Aarset, M.V. (1987). How to identify bathtub hazard rate. IEEE Trans. Reliab., R-36, 106–108. · Zbl 0625.62092 · doi:10.1109/TR.1987.5222310
[2] Bebbington, M., Lai, C.D. and Zitikis, R. (2006). Changing phases of human life expectancy: can we find them mathematically? In Proceedings of the UNU–WIDER Conference on Advancing Health Equity. United Nations University–World Institute for Development Economics Research (UNU–WIDER), Helsinki, September.
[3] Bebbington, M., Lai, C.D. and Zitikis, R. (2007a). Modeling human mortality using mixtures of bathtub shaped failure distributions. J. Theor. Biol., 245, 528–538. · doi:10.1016/j.jtbi.2006.11.011
[4] Bebbington, M., Lai, C.D. and Zitikis, R. (2007b). A flexible Weibull extension. Reliab. Eng. Syst. Safety, 92, 719–726. · doi:10.1016/j.ress.2006.03.004
[5] Bebbington, M., Lai, C.D. and Zitikis, R. (2008). Reduction in mean residual life in the presence of a constant competing risk. Appl. Stoch. Models Bus. Ind., 24, 51–63. · Zbl 1164.90007 · doi:10.1002/asmb.693
[6] Berger, J.O. and Pericchi, L.R. (1996). The intrinsic Bayes factor for model selection and prediction. J. Am. Stat. Assoc., 91, 109–122. · Zbl 0870.62021 · doi:10.1080/01621459.1996.10476668
[7] Block, H. W. and Joe, H. (1997). Tail behavior of the failure rate functions of mixtures. Lifetime Data Anal., 3, 269–288. · Zbl 0887.62100 · doi:10.1023/A:1009653032333
[8] Block, H.W. and Savits, T.H. (1997). Burn-in. Stat. Sci., 12, 1–19. · doi:10.1214/ss/1029963258
[9] Block, H.W., Jong, Y.K. and Savits, T.H. (1999). Bathtub functions and burn-in. Probab. Eng. Inform. Sci., 13, 497–507. · Zbl 0969.90034
[10] Celeux, G. and Diebolt, J. (1992). A stochastic approximation type EM algorithm for the mixture problem. Stochastics and Stochastic Reports, 41, 119–134. · Zbl 0766.62050 · doi:10.1080/17442509208833797
[11] Dempster, A.P. (1974). The direct use of likelihood for significance testing. In Proc. Conference on foundational questions in Statistical inference. University of Aarhus, pp. 335–352. · Zbl 0367.62004
[12] Devroye, L. (1986). Non-uniform random variate generation. Springer-Verlag, New York. · Zbl 0593.65005
[13] Diebolt, J. and Robert, C.P. (1994). Estimation of finite mixture distributions through Bayesian sampling. J. R. Stat. Soc., Ser. B, 56, 363–375. · Zbl 0796.62028
[14] Dimitrakopoulou, T., Adamidis, K. and Loukas, S. (2007). A lifetime distribution with an upside-down bathtub-shaped hazard function. IEEE Trans. Reliab., 56, 308–311. · doi:10.1109/TR.2007.895304
[15] Geisser, S. and Eddy, W.F. (1979). A predictive approach to model selection. J. Am. Stat. Assoc., 74, 153–160. · Zbl 0401.62036 · doi:10.1080/01621459.1979.10481632
[16] Gelfand, A.E. (1996). Model determination using sampling based methods. In Markov Chain Monte Carlo in Practice, (W.R. Gilks, S. Richardson and D.J. Spiegelhalter, eds.). Chapman and Hall, London, pp. 145–161. · Zbl 0840.62003
[17] Gelfand, A.E. and Ghosh, S.K. (1998). Model choice: a minimum posterior predictive loss approach. Biometrika, 85, 1–11. · Zbl 0904.62036 · doi:10.1093/biomet/85.1.1
[18] Ghosh, J.K. and Samanta, T. (2002). Non subjective Bayes testing – an overview. J. Stat. Plan. Inf., 103, 205–223. · Zbl 0989.62017 · doi:10.1016/S0378-3758(01)00222-1
[19] Gilks, W.R. and Wild, P. (1992). Adaptive rejection sampling for Gibbs sampling. App. Stat., 41, 337–348. · Zbl 0825.62407 · doi:10.2307/2347565
[20] Gupta, A., Mukherjee, B. and Upadhyay, S.K. (2008). Weibull extension model: a Bayes study using Markov chain Monte Carlo simulation. Reliab. Eng. Syst. Safety, 93, 1434–1443. · doi:10.1016/j.ress.2007.10.008
[21] Gurvich, M.R., Dibenedetto, A.T. and Ranade, S.V. (1997). A new statistical distribution for characterizing the random strength of brittle materials. J. Mater. Sci., 32, 2559–2564. · doi:10.1023/A:1018594215963
[22] Jaisingh, L.R., Dey, D.K. and Griffith, W.S. (1993). Properties of multivariate survival distribution generated by Weibull and inverse gamma mixtures. IEEE Trans. Reliab., 42, 618–622. · Zbl 0799.60086 · doi:10.1109/24.273591
[23] Jiang, R. and Murthy, D.N.P. (1999). The exponentiated Weibull family: a graphical approach. IEEE Trans. Reliab., 48, 68–72. · Zbl 04552915 · doi:10.1109/24.765929
[24] Krohn, C.A. (1969). Hazard versus renewal rate of electronic items. IEEE Trans. Reliab., R-18, 64–73. · doi:10.1109/TR.1969.5216979
[25] Lai, C.D., Xie, M. and Murthy, D.N.P. (2003). A modified Weibull distribution. IEEE Trans. Reliab., 52, 33–37. · doi:10.1109/TR.2002.805788
[26] Laud, P.W. and Ibrahim, J.G. (1995). Predictive model selection. J. R. Stat. Soc., Ser. B, 57, 247–262. · Zbl 0809.62024
[27] Mann, N.R., Schafer, R.E. and Singpurwalla, N.D. (1974). Methods for statistical analysis of reliability and life data. John Wiley, New York. · Zbl 0339.62070
[28] Martz, H.F., and Waller, R.A. (1982). Bayesian reliability analysis. John Wiley, New York. · Zbl 0597.62101
[29] Mudholkar, G.S. and Hutson, A.D. (1996). The exponentiated Weibull family: some properties and a flood data application. Commun. Stat. - Theor. Meth., 25, 3059–3083. · Zbl 0887.62019 · doi:10.1080/03610929608831886
[30] Mudholkar, G.S. and Srivastava, D.K. (1993). Exponentiated Weibull family for analyzing bathtub failure rate data. IEEE Trans. Reliab., 42, 299–302. · Zbl 0800.62609 · doi:10.1109/24.229504
[31] Mudholkar, G.S, Srivastava, D.K. and Freimer, M. (1995). The exponentiated Weibull family – a reanalysis of the bus-motor-failure data. Technometrics, 37, 436–445. · Zbl 0900.62531 · doi:10.1080/00401706.1995.10484376
[32] Mudholkar, G.S, Srivastava, D.K. and Kollia, G.D. (1996). A Generalization of the Weibull distribution with application to the analysis of survival data. J. Am. Stat. Assoc., 91, 1575–1583. · Zbl 0881.62017 · doi:10.1080/01621459.1996.10476725
[33] Nadarajah, S. (2005). On the moments of the modified Weibull distribution. Reliab. Eng. Syst. Safety, 90, 114–117. · doi:10.1016/j.ress.2004.09.002
[34] Patra, K. and Dey, D.K. (1999). A multivariate mixture of Weibull distribution in reliability models. Stat. Probab. Lett., 45, 225–235. · Zbl 1055.62554 · doi:10.1016/S0167-7152(99)00062-0
[35] Sahu, S.K. and Dey, D.K. (2000). A comparison of frailty and other models for bivariate survival data. Lifetime Data Anal., 6, 207–228. · Zbl 0966.62086 · doi:10.1023/A:1009633524403
[36] Spiegelhalter, D.J., Best, N.G., Carlin, B.P. and Vander Linde, A. (2002). Bayesian measures of model complexity and fit. J. R. Stat. Soc., Ser. B, 64, 583–639. · Zbl 1067.62010 · doi:10.1111/1467-9868.00353
[37] Tang, Y., Xie, M. and Goh, T.N. (2003). Statistical analysis of a Weibull extension model. Commun. Stat. - Theor. Meth., 32, 913–928. · Zbl 1107.62369 · doi:10.1081/STA-120019952
[38] Upadhyay, S.K. and Gupta, A. (2010). Bayesian analysis of modified Weibull distribution using Markov Chain Monte Carlo simulation. J. Stat. Comp. Simul., 80, 241–254. · Zbl 1187.62058 · doi:10.1080/00949650802600730
[39] Upadhyay, S.K. and Smith, A.F.M. (1994). Modeling complexities in reliability and the role of simulation in Bayesian computation. Int. J. Cont. Eng. Ed., 4, 93–104.
[40] Upadhyay, S.K., Vasishta, N. and Smith, A.F.M. (2001). Bayes inference in life testing and reliability via Markov chain Monte Carlo simulation. Sankhya, Ser. A, 63, 15–40. · Zbl 0995.62505
[41] Vaupel, J.W. and Yashin A.I. (1985). Heterogeneity’s ruses: some surprising effects of selection on population dynamics. Am. Stat., 39, 176–184.
[42] Wang, F.K. (2000). A new model with bathtub-shaped failure rate using an additive Burr XII distribution. Reliab. Eng. Syst. Safety, 70, 305–312. · doi:10.1016/S0951-8320(00)00066-1
[43] Weibull, W. (1951). A statistical distribution function of wide applicability. J. Appl. Mech., 18, 293–297. · Zbl 0042.37903
[44] Wondmagegnehu, E.T., Navarro, J. and Hernandez, P.J. (2005). Bathtub shaped failure rates from mixtures: a practical point of view. IEEE Trans. Reliab., 54, 270–275. · doi:10.1109/TR.2005.847271
[45] Xie, M. and Lai, C.D. (1996). Reliability analysis using an additive Weibull model with bathtub-shaped failure rate function. Reliab. Eng. Syst. Safety, 52, 87–93. · doi:10.1016/0951-8320(95)00149-2
[46] Xie, M., Tang, Y. and Goh, T.N. (2002). A modified Weibull extension with bathtub-shaped failure rate function. Reliab. Eng. Syst. Safety, 76, 279–285. · doi:10.1016/S0951-8320(02)00022-4
[47] Zhang, T.L. and Xie, M. (2007). Failure data analysis with extended Weibull distribution. Commun. Stat. Simul. Comput., 36, 579–592. · Zbl 1121.62090 · doi:10.1080/03610910701236081
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.