A Random Effects Model for Multivariate Life Data
The Weibull distribution is a natural starting point in the modelling of failure times and material strength data. In recent years there has been a growing interest in the modelling of heterogeneity within this context. A natural approach is to consider a mixture, either discrete or continuous, of Weibull distributions. A judicious choice of mixing distribution can lead to a tractable and flexible generalization of the Weibull distribution. An example is the Burr distribution, which is a gamma mixture of Weibull distributions, and this is used in the paper to illustrate the approach. Some relevant statistical methods are introduced and various applications are discussed.
KeywordsRandom Effect Model Weibull Distribution Failure Time Weibull Model Covariate Information
Unable to display preview. Download preview PDF.
- Crowder, M.J. and Kimber, A.C. (1994), “A Score Test for the Multivariate Burr and Other Weibull Mixture Distributions,” Submitted for publication.Google Scholar
- Crowder, M.J., Kimber, A.C., Smith, R.L. and Sweeting, T.J. (1991), Statistical Analysis of Reliability Data. London: Chapman and Hall.Google Scholar