Background
Type: Article

The beta exponential-geometric distribution

Journal: Communications in Statistics Part B: Simulation and Computation (15324141)Year: 2012Volume: 41Issue: Pages: 1606 - 1622
DOI:10.1080/03610918.2011.611309Language: English

Abstract

A new four-parameter distribution with decreasing, increasing, and upside-down bathtub failure rate called the beta exponential-geometric distribution is proposed. The new distribution, generated from the logit of a beta random variable, extends the exponential-geometric distribution of Adamidis and Loukas (1998) and some other distributions. A comprehensive mathematical treatment of this distribution is provided. Some expressions for the moment generating function, moments, order statistics, and Rényi entropy of the new distribution are derived. Estimation of the stress-strength parameter is also obtained. The model parameters are estimated by the maximum likelihood method and Fisher information matrix is discussed. Finally, an application to a real data set is illustrated. Copyright © Taylor & Francis Group, LLC.