الفهرس | Only 14 pages are availabe for public view |
Abstract Sometimes the known statistical distributions do not suit the available data; accordingly generating a new distribution is needed. The aim of this paper was to introduce two new distributions. The first one is a one-parameter distribution which is referred to as NLM(Ý) and the second one is a power transformation of the first distribution. We refer to the second distribution as NLMP(Ü,Ý). The hazard function of NLMP(Ü,Ý) can be constant, decreasing, bathtub, decreasing - increasing, and increasing. This variety of shapes of its hazard function enables NLMP(Ü, Ý) to fit different data sets. The maximum likelihood estimate of the two parameters of NLMP(Ü,Ý) were obtained and a simulation study was carried out to examine the accuracy of the maximum likelihood estimators of the NLMP(Ü,Ý) parameters as well as the coverage probability and average width of the confidence intervals for both parameters |