Abstract
The Weibull distribution is composited with Pareto model to obtain a flexible, reliable long-tailed parametric distribution for modeling unimodal failure rate data. The hazard function of the composite family accommodates decreasing and unimodal failure rates, which are separated by the boundary line of the space of shape parameter, gamma, when it equals to a known constant. The least square and maximum likelihood parameter estimation techniques are discussed. The advantages of using the proposed family are demonstrated and compared by illustrating well-known examples: guinea pigs survival time data, head and neck cancer data, and nasopharynx cancer survival data.
Original language | English |
---|---|
Pages (from-to) | 1901-1915 |
Number of pages | 15 |
Journal | Communications in Statistics - Theory and Methods |
Volume | 38 |
Issue number | 11 |
DOIs | |
State | Published - Jan 2009 |
Keywords
- Kaplan-Meier curve
- Pareto
- Right censoring
- Unimodal failure rate
- Weibull