Revisiting the memoryless property – testing for the Pareto type I distribution
arxiv(2024)
摘要
We propose new goodness-of-fit tests for the Pareto type I distribution.
These tests are based on a multiplicative version of the memoryless property
which characterises this distribution. We present the results of a Monte Carlo
power study demonstrating that the proposed tests are powerful compared to
existing tests. As a result of independent interest, we demonstrate that tests
specifically developed for the Pareto type I distribution substantially
outperform tests for exponentiality applied to log-transformed data (since
Pareto type I distributed values can be transformed to exponentiality via a
simple log-transformation). Specifically, the newly proposed tests based on the
multiplicative memoryless property of the Pareto distribution substantially
outperform a test based on the memoryless property of the exponential
distribution. The practical use of tests is illustrated by testing the
hypothesis that two sets of observed golfers' earnings (those of the PGA and
LIV tours) are realised from Pareto distributions.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要