The Generalized Waring Process and Its Application |
| |
Authors: | Evdokia Xekalaki Mimoza Zografi |
| |
Affiliation: | 1. Department of Statistics , Athens University of Economics and Business , Athens, Greece;2. Department of Statistics , University of California , Berkeley, California, USA exek@aueb.gr;4. Department of Statistics , Athens University of Economics and Business , Athens, Greece |
| |
Abstract: | The generalized Waring distribution is a discrete distribution with a wide spectrum of applications in areas such as accident statistics, income analysis, environmental statistics, etc. It has been used as a model that better describes such practical situations as opposed to the Poisson distribution or the negative binomial distribution. Associated to both the Poisson and negative binomial distributions are the well-known Poisson and Pólya processes. In this article, the generalized Waring process is defined. Two models have been shown to lead to the generalized Waring process. One is related to a Cox process, while the other is a compound Poisson process. The defined generalized Waring process is shown to be a stationary, but non homogenous Markov process. Several properties are studied and the intensity, individual intensity, and Chapman–Kolmogorov differential equations of it are obtained. Moreover, the Poisson and Pólya processes are shown to arise as special cases of the generalized Waring process. Using this fact, some known results and some properties of them are obtained. |
| |
Keywords: | Accident proneness Accident liability Cox process Chapman–Kolmogorov equations Individual intensity Markovian property Pólya process Transition probabilities Stationary increments |
|
|