The newly modified Weibull distribution defined in the literature is a model based on combining the Weibull and modified Weibull distributions. It has been demonstrated as the best model for fitting to the bathtub-shaped failure rate data sets. However, another new model based on combining the modified Weibull and Gompertz distributions has been demonstrated later to be even better than the first model. In this article, we have shown how to improve the former model into a better model, and more importantly, we have provided a full Bayesian analysis of the improved model. The Hamiltonian Monte Carlo and cross-entropy methods have been exploited to empower the traditional methods of statistical estimation. Bayes estimators have been obtained using Hamiltonian Monte Carlo for posterior simulations. Bayesian model checking has also been provided in order to check the validation of the model when fitting to real data sets. We have also provided the maximum likelihood estimators of the model parameters using the cross-entropy method to optimize the log-likelihood function. The results derived from the analysis of two well-known data sets show that the improved model is much better than its original form.
GompertzB.On the nature of the function expressive of the law of human mortality and on the new model of determining the value of life contingencies. Philos T R Soc Lond1825; 115: 513–585.
5.
GuptaAMukherjeeBUpadhyaySK.Weibull extension model: a Bayes study using Markov chain Monte Carlo simulation. Reliab Eng Syst Safe2008; 93(10): 1434–1443.
6.
UpadhyaySKGuptaA.A Bayesian analysis of modified Weibull distribution using Markov Chain Monte Carlo simulation. J Stat Comput Sim2010; 80(3): 241–254.
7.
ThachTTBrisR.Reparameterized Weibull distribution: a Bayes study using Hamiltonian Monte Carlo. In: BeerMZioE (eds) Proceedings of the 29th European safety and reliability conference. Singapore: Research Publishing, 2019, pp.997–1004.
8.
XieMLaiCD.Reliability analysis using an additive Weibull model with bathtub-shaped failure rate function. Reliab Eng Syst Safe1995; 52: 87–93.
NealRM.MCMC using Hamilton dynamics. In: BrooksSGelmanAJonesG, et al. (eds) Handbook of Markov chain Monte Carlo. Boca Raton, FL: CRC Press, 2011, pp.113–162.
12.
GelmanACarlinJBSternHS, et al. Bayesian data analysis. 3rd ed.Boca Raton, FL: CRC Press, 2014, pp.300–310.
MetropolisNRosenbluthAWRosenbluthMN, et al. Equation of state calculations by fast computing machines. J Chem Phys1953; 21: 1087–1092.
15.
AlderBWainwrightT.Studies in molecular dynamics I. General method. J Chem Phys1959; 31(2): 459–466.
16.
DuaneSKennedyADPendletonBJ, et al. Hybrid Monte Carlo. Phys Lett B1987; 195(2): 216–222.
17.
NealRM.Bayesian learning for neural networks (Lecture notes in statistics 118). New York: Springer, 1996
18.
HoffmanMDGelmanA.The No-U-Turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo. J Mach Learn Res2014; 15: 1593–1623.
19.
JiangHXieMTangLC.Markov chain Monte Carlo methods for parameter estimation of the modified Weibull distribution. J Appl Stat2008; 35(6): 647–658.
20.
KunduDHowladerH.Bayesian inference and prediction of the inverse Weibull distribution for type-II censored data. Comput Stat Data An2010; 54(6): 1547–1558.
21.
Stan Development Team. RStan: the R interface to Stan. R package version 2.18.2, http://mc-stan.org/rstan/
22.
Stan Development Team. Stan modeling language user’s guide and reference manual, http://mc-stan.org/
23.
SinhaSKSloanJA.Bayes estimation of the parameters and reliability function of the 3-parameter Weibull distribution. IEEE T Reliab1988; 37(4): 364–369.
24.
UpadhyaySKGuptaAMukherjeeB, et al. A Bayes comparison of Weibull extension and modified Weibull models for data showing bathtub hazard rate. J Stat Comput Sim2013; 83(1): 68–81.
25.
UpadhyaySKGuptaADeyDK.Bayesian modeling of bathtub shaped hazard rate using various Weibull extensions and related issues of model selection. Sankhya B2012; 74: 15.
26.
KunduD.Bayesian inference and life testing plan for the Weibull distribution in presence of progressive censoring. Technometrics2008; 50(2): 144–154.
27.
SolimanAAAbd-EllahAHAbou-ElheggagNA, et al. Modified Weibull model: a Bayes study using MCMC approach based on progressive censoring data. Reliab Eng Syst Safe2012; 100: 48–57.
28.
SultanKSAlsadatNHKunduD.Bayesian and maximum likelihood estimations of the inverse Weibull parameters under progressive type-II censoring. J Stat Comput Sim2014; 84(10): 2248–2265.
29.
GuureCBIbrahimNAAdamMB, et al. Bayesian parameter and reliability estimate of Weibull failure time distribution. B Malays Math Sci So2014; 37: 611–632.
30.
GelmanA.Comment: fuzzy and Bayesian p-values and u-values. Stat Sci2005; 20: 380–381.
31.
SpiegelhalterDJBestNGCarlinBP, et al. The deviance information criterion: 12 years on. J Roy Stat Soc B2014; 76(3): 485–493.
32.
BanerjeeSCarlinBPGelfandAE.Hierarchical modeling and analysis for spatial data. 2nd ed.Boca Raton, FL: CRC Press, 2014.
33.
XieMTangYGohTN.A modified Weibull extension with bathtub-shaped failure rate function. Reliab Eng Syst Safe2002; 76: 279–285.
AarsetMV.How to identify bathtub hazard rate. IEEE T Reliab1987; 36(1): 106–108.
36.
ShakhatrehMKLemonteAJMoreno–ArenasG.The log-normal modified Weibull distribution and its reliability implications. Reliab Eng Syst Safe2019; 188: 6–22.
