A new test for tail index with application to Danish fire loss data
Authors:
- 21 July 2021
- journal article
- research article
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 91 (18) , 3880-3893
Abstract
The conditional approach of Hill's estimator depends on a threshold choice. This may give different results in a statistical test when different thresholds are used. Motivated by the uniformly most powerful test, this article proposes a new test for heavy tail of various degrees. Simulation shows that the test is applicable and its power is superior to three existing methods in the literature. An example of the Danish fire loss data elucidates the inconsistent conclusion in existing statistical tests and demonstrates the consistent conclusion the proposed test leads to. A new and affirmative insight into the data is that the variance does not exist.Keywords
Funding Information
- HKSAR GRF (17304417)
- Education University of Hong Kong
- research startup fund (RG 44/2019-2020R)
This publication has 21 references indexed in Scilit:
- A Maximized Sequential Probability Ratio Test for Drug and Vaccine Safety SurveillanceSequential Analysis, 2011
- A Diagnostic for Selecting the Threshold in Extreme Value AnalysisJournal of the Royal Statistical Society Series B: Statistical Methodology, 2001
- Tail-Index Estimates in Small SamplesJournal of Business & Economic Statistics, 2001
- Smoothing the Hill EstimatorAdvances in Applied Probability, 1997
- Laws of Large Numbers for Sums of Extreme ValuesThe Annals of Probability, 1982
- A Sequential Clinical Trial for Testing $p_1 = p_2$The Annals of Statistics, 1980
- A Simple General Approach to Inference About the Tail of a DistributionThe Annals of Statistics, 1975
- Locally Most Powerful Sequential TestsThe Annals of Statistics, 1975
- Statistical Inference Using Extreme Order StatisticsThe Annals of Statistics, 1975
- Sequential Tests of Statistical HypothesesThe Annals of Mathematical Statistics, 1945