|
Activity Number:
|
134
- Bayesian Modeling
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 9, 2021 : 1:30 PM to 3:20 PM
|
|
Sponsor:
|
Section on Statistical Computing
|
|
Abstract #318254
|
|
|
Title:
|
Quantile Regression on COVID-19
|
|
Author(s):
|
Andrew Kenig* and Mei Ling Huang
|
|
Companies:
|
Brock University and Brock University
|
|
Keywords:
|
Conditional quantile;
COVID-19;
extreme value distribution;
Burr distribution;
generalized Pareto distribution;
Nonparametric Regression
|
|
Abstract:
|
The COVID-19 pandemic is an extreme disaster for the world during 2020-2021. To improve management and prediction on this event is an important task. Quantile regression estimates conditional quantiles. Estimating extreme conditional quantiles is a difficult problem. The regular quantile regression method often sets a linear model with estimating the coefficients to obtain the estimated conditional quantile. That approach may be restricted by the model setting, and computational difficulties. To overcome these difficulties, this paper proposes a nonparametric quantile regression method with a five-step algorithm. Monte Carlo simulations show good efficiency for the proposed nonparametric quantile regression relative to the regular linear quantile regression. This paper studies Canada Ontario COVID-19 pandemic example by using the proposed method. Comparisons of the proposed method with existing methods are given.
|
Authors who are presenting talks have a * after their name.
