Goodness of fit for the Waring distribution

Abstract

The Waring distribution is an important two-parameter discrete distribution, commonly used in fields such as ecology, linguistics, and information science, where heavy tails are often observed. In this paper, we propose a new goodness-of-fit test for the Waring distribution, which is established through the hazard rate and a linear equivalent definition of the Waring distribution. We establish an asymptotic Chi-square null distribution for the proposed test and show that it is more powerful than classical methods in simulation studies. Finally, we apply the test to analyze the authorships of published papers on computer science.

Keywords

• Waring distribution
• goodness-of-fit test
• long-tailed distribution
• hazard rate