Journal of Statistics: Advances in Theory and ApplicationsAuthor's: Hafida Goual and Nacira Seddik-Ameur
Pages: [275] - [305]
Received Date: December 7, 2016
Submitted by:
DOI: http://dx.doi.org/10.18642/jsata_7100121749
In this paper, we have proposed and study a new five parameter generalized inverse Weibull model that is based on the cumulative distribution function of Kumaraswamy [14] distribution. The importance of this model lies in its ability to model a monotone and non-monotone failure rate functions, which are quite common to lifetime data analysis and reliability. We present a new goodness-of-fit test proposed by Bagdonavicius and Nikulin [2] for the Kumaraswamy generalized inverse Weibull model in the case of censored data. The method of maximum likelihood is used to estimate the model parameters. We illustrate the model and the proposed test by applications to two real data sets.
censored data, generalized inverse Weibull distribution, information matrix, Kumaraswamy distribution, maximum likelihood estimation, Nikulin Rao Robson statistic.
