An Alternative Goodness-of-fit Test for a Gamma Distribution Based on the Independence Property

Abstract

The focus of this study is primarily on testing whether data come from a gamma distribution, one of the most important distributions used to model physial quantities that take positive values. To this end, a test statistic has been developed based on the independence property ofa gama distribution. The proposed test statistic is asumptotically distributed as standard normal under the null hypothesis as the sample size approaches infinity. Extensive simulation studies indicate that the performance of the proposed test is substantially better than existing tests reported in the literature, especially in caess with samples of moderate size. The test has also been applied to honey bee transit time data to demonstrate the efficacy of the new test statistic.