A new generalization of the geometric distribution with parameters α>0 and 0<θ<1 is obtained in this paper. This can be done either by using the Marshall and Olkin (Biometrika 84(3), 641–652, 1997) scheme and adding a parameter to the geometric distribution or by starting with the generalized exponential distribution in Marshall and Olkin (Biometrika 84(3), 641–652, 1997) and discretizing this continuous distribution. The particular case α=1 led us to the geometric distribution. After reviewing some of its properties, we investigated the question of parameter estimation. The new distribution is unimodal with a failure rate that is monotonically increasing or decreasing, depending on the value of the parameter α. Expected frequencies were calculated for two overdispersed and infradispersed examples, and the distribution was found to provide a very satisfactory fit.
Branching process Discretizing Failure rate Fitting Geometric distribution
Mathematics Subject Classification (2000)
60E05 62E99 60J80
This is a preview of subscription content, log in to check access.
Farrington CP, Grant D (1999) The distribution of time to extinction in subcritical branching process: applications to outbreak of infectious disease. J Appl Probab 36:771–779
Kemp AW (2008) The discrete half-normal distribution. In: Advances in mathematical and statistical modeling. Birkhäuser, Basel, pp 353–365
Krishna H, Singh P (2009) Discrete Burr and discrete Pareto distributions. Stat Methodol 6(2):177–188
Makc̆utek J (2008) A generalization of the geometric distribution and its application in quantitative linguistics. Romanian Rep Phys 60(3):501–509
Marshall AW, Olkin I (1997) A new method for adding a parameter to a family of distributions with application to the exponential and Weibull families. Biometrika 84(3):641–652