Online Program Home
My Program

Abstract Details

Activity Number: 131 - Simulation and MCMC
Type: Contributed
Date/Time: Monday, July 30, 2018 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Computing
Abstract #329169
Title: A Direct Quantile Regression
Author(s): Rachel Morris* and Mei Ling Huang
Companies: Brock University and Brock University
Keywords: Conditional quantile; goodness of fit; Extreme value distribution; Gumbel's second kind of bivariate exponential distribution; nonparametric regression; loss function

Estimating high conditional quantiles is an important problem. Many studies on this problem use a quantile regression (QR) method. The regular quantile regression method often sets a linear or non-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 paper proposes a direct nonparametric quantile regression method to overcome this restriction. The paper studies the asymptotic properties of this direct estimator. Monte Carlo simulations show good efficiency for the proposed nonparametric QR estimator relative to the regular QR estimator. The paper also investigates a real-world example of applications by using the proposed method, and gives comparisons of the proposed method and existing methods.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program