Activity Number:
|
494
- Simulation-Based Approaches
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 6, 2020 : 10:00 AM to 2:00 PM
|
Sponsor:
|
Section on Statistical Computing
|
Abstract #309734
|
|
Title:
|
A Two-Stage Nonparametric Quantile Regression
|
Author(s):
|
Mei Ling Huang and Rachel Clemens*
|
Companies:
|
Brock University and Brock University
|
Keywords:
|
Conditional quantile;
extrapolation;
Extreme value distribution;
Fréchet distribution;
goodness of fit;
Multivariate kernel density estimation
|
Abstract:
|
Estimating extreme conditional quantiles is an important problem. Many studies on this problem use a quantile regression (QR) method. The regular QR method often sets a linear model, which estimates the coefficients in the model to obtain the estimated conditional quantile. The real-world applications may be restricted by this approach's model setting. This project proposes a two-stage direct nonparametric extrapolation quantile regression method to overcome this restriction. Monte Carlo simulations show good efficiency for the proposed direct nonparametric QR extrapolation estimator relative to the linear QR extrapolation estimator. This project also investigates an example of rainfall in Toronto, Canada using the proposed method with comparisons to the linear methods.
|
Authors who are presenting talks have a * after their name.