Article ID Journal Published Year Pages File Type
1151222 Statistical Methodology 2006 10 Pages PDF
Abstract

An extended form of Weibull distribution is suggested which has two shape parameters (mm and δδ). Introduction of another shape parameter δδ helps to express the extended Weibull distribution not only as an exact form of a mixture of distributions under certain conditions, but also provides extra flexibility to the density function over positive range. The shape of density function of the extended Weibull type distribution for various values of the parameters is shown which may be of some interest to Bayesians. Certain statistical properties such as hazard rate function, mean residual function, rrth moment are defined explicitly. The proposed extended Weibull distribution is used to derive an exact form of two, three and kk-component mixture of distributions. With the help of a real data set, the usefulness of mixture Weibull type distribution is illustrated by using Markov Chain Monte Carlo (MCMC), Gibbs sampling approach.

Related Topics
Physical Sciences and Engineering Mathematics Statistics and Probability
Authors
, ,