|
Activity Number:
|
347
- Nonparametric Hybrid Methods
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2020 : 10:00 AM to 2:00 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
|
Abstract #313107
|
|
|
Title:
|
Quantile Regression for Asynchronous Longitudinal Data
|
|
Author(s):
|
Xuerui Li* and Yuanshan Wu and Yanyan Liu
|
|
Companies:
|
University of Michigan, Ann Arbor; Wuhan University, China and Zhongnan University of Economics and Law, China and Wuhan University, China
|
|
Keywords:
|
Quantile regression;
Asynchronous longitudinal data;
Kernel-smoothing;
Local polynomial
|
|
Abstract:
|
Emergence of sparse asynchronous longitudinal data with mismatched time-dependent responses and covariates accompanying with typically skewed response in many medical re- searches has driven the recent interest in statistical regression and inference. Estimating equation works in principle, but may suffer from an efficiency loss. Considering the quan- tile regression is a powerful complement to the usual mean regression and allows skewed distribution and error heteroscedasticity, this paper proposes a kernel weighting method for explicating the mismatch under time-invariant and time-dependent coefficients quantile re- gression models. Furthermore, the asymptotic behaviors of the estimators are examined. A simulation study is carried out to illustrate the performance of the proposed. An empirical application of the model to real data further demonstrates the potential of the proposed modeling procedures.
|
Authors who are presenting talks have a * after their name.
