A new lifetime model with decreasing,increasing, bathtub-shaped,and upside-down bathtub-shaped hazard rate function

A new three-parameter distribution with decreasing, increasing, bathtub-shaped and upside-down bathtub-shaped hazard rate function is proposed. The new distribution encompasses some previously known distributions as special cases. Basic mathematical properties of the new distribution (including the moment-generating function, moments, order statistics properties, Rényi entropy and stress–strength parameter) are derived. Its parameters are estimated by the method of maximum likelihood. An application is illustrated using a real data set.     

The Kotz-type distribution with applications

The Kotz-type distribution was introduced by Kotz (1975) as a generalization of the multivariate normal distribution. Since 1990 there has been a surge of activity relating to this distribution. We have identified some 25 papers on the Kotz-type distribution over the period from 1990 to 2002 - compared to just 5 over the period from 1980 to 1989. The aim of this paper is to review the developments in the following areas: marginal distributions; moments; characteristic functions; characterizations; asymptotics; quadratic forms; estimation; hypothesis testing; generalizations; Bayesian inference; and, applications in other areas such as ecology, discriminant analysis, mathematical finance, repeated measurements, shape theory and signal processing. We feel that this review could be important as a source of reference and for unlocking further research on the distribution.     

Useful moment and CDF formulations for the COM–Poisson distribution

The Poisson distribution is as important for discrete events as the normal distribution is to large sample data. In this note, we discuss a generalized Poisson distribution recently introduced in the statistics literature. We derive—for the first time—exact and explicit expressions for its moments and the cumulative distribution function for the case of over-dispersion. Computational issues are discussed to show the real value of these expressions.     

An Expression for Fast Computation of Sample Central Moments

An expression is provided for the expectation of sample central moments. It is practical and offers computational advantages over the original form due to Kong (The American Statistician, 65, 2011, 198–199).