Abstract
Based on the idea of evaluating the distribution of the ‘odds of death’ of a lifetime variable, the odd Weibull distribution proposed by Cooray has recently been shown to be useful for testing the goodness of fit of the Weibull and inverse Weibull distributions. The model is also very versatile in modelling lifetime data in that its failure rate function can be increasing, decreasing, constant, bathtub shaped, and unimodal. In this paper, a detailed parametric characterization of the statistical properties of this distribution is carried out. The shapes of the Weibull probability plot with different model parameters are presented and the graphic parameter estimation steps are iterated. Burn-in and useful period-related issues of the bathtub-shaped failure rate curve are discussed. An application example is shown to illustrate the parameter estimation procedure and the superior fit of the model for some real data to the two-parameter Weibull distribution and some other three-parameter Weibull-related distributions. © 2008, Institution of Mechanical Engineers. All rights reserved.
| Original language | English |
|---|---|
| Pages (from-to) | 583-594 |
| Journal | Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability |
| Volume | 222 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - 1 Dec 2008 |
| Externally published | Yes |
Research Keywords
- bathtub-shaped curve
- burn-in
- extreme value property
- failure rate function
- odd Weibull distribution
- useful period
- Weibull probability plot