High quantile regression for extreme events
Abstract For extreme events, estimation of high conditional quantiles for heavy tailed distributions is an important problem. Quantile regression is a useful method in this field with many applications. Quantile regression uses an L 1-loss function, and an optimal solution by means of linear program...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2017-05-01
|
Series: | Journal of Statistical Distributions and Applications |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s40488-017-0058-3 |
id |
doaj-077553e9c2bb440e81a2c2be62027919 |
---|---|
record_format |
Article |
spelling |
doaj-077553e9c2bb440e81a2c2be620279192020-11-25T00:21:26ZengSpringerOpenJournal of Statistical Distributions and Applications2195-58322017-05-014112010.1186/s40488-017-0058-3High quantile regression for extreme eventsMei Ling Huang0Christine Nguyen1Department of Mathematics & Statistics, Brock UniversityDepartment of Mathematics & Statistics, Brock UniversityAbstract For extreme events, estimation of high conditional quantiles for heavy tailed distributions is an important problem. Quantile regression is a useful method in this field with many applications. Quantile regression uses an L 1-loss function, and an optimal solution by means of linear programming. In this paper, we propose a weighted quantile regression method. Monte Carlo simulations are performed to compare the proposed method with existing methods for estimating high conditional quantiles. We also investigate two real-world examples by using the proposed weighted method. The Monte Carlo simulation and two real-world examples show the proposed method is an improvement of the existing method.http://link.springer.com/article/10.1186/s40488-017-0058-3Bivariate Pareto distributionConditional quantileExtreme value distributionGeneralized Pareto distributionLinear programmingWeighted loss function |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mei Ling Huang Christine Nguyen |
spellingShingle |
Mei Ling Huang Christine Nguyen High quantile regression for extreme events Journal of Statistical Distributions and Applications Bivariate Pareto distribution Conditional quantile Extreme value distribution Generalized Pareto distribution Linear programming Weighted loss function |
author_facet |
Mei Ling Huang Christine Nguyen |
author_sort |
Mei Ling Huang |
title |
High quantile regression for extreme events |
title_short |
High quantile regression for extreme events |
title_full |
High quantile regression for extreme events |
title_fullStr |
High quantile regression for extreme events |
title_full_unstemmed |
High quantile regression for extreme events |
title_sort |
high quantile regression for extreme events |
publisher |
SpringerOpen |
series |
Journal of Statistical Distributions and Applications |
issn |
2195-5832 |
publishDate |
2017-05-01 |
description |
Abstract For extreme events, estimation of high conditional quantiles for heavy tailed distributions is an important problem. Quantile regression is a useful method in this field with many applications. Quantile regression uses an L 1-loss function, and an optimal solution by means of linear programming. In this paper, we propose a weighted quantile regression method. Monte Carlo simulations are performed to compare the proposed method with existing methods for estimating high conditional quantiles. We also investigate two real-world examples by using the proposed weighted method. The Monte Carlo simulation and two real-world examples show the proposed method is an improvement of the existing method. |
topic |
Bivariate Pareto distribution Conditional quantile Extreme value distribution Generalized Pareto distribution Linear programming Weighted loss function |
url |
http://link.springer.com/article/10.1186/s40488-017-0058-3 |
work_keys_str_mv |
AT meilinghuang highquantileregressionforextremeevents AT christinenguyen highquantileregressionforextremeevents |
_version_ |
1725362778954268672 |