摘要
Longitudinal data arise frequently in many economic studies and epidemiological research. In this paper, we investigate the partially linear additive model for longitudinal data in the framework of quantile regression. To incorporate the within-subject correlation, we develop an estimation procedure using quadratic inference QIF) and polynomial spline approximation for unknown nonparametric functions. The theoretical properties of the resulting estimators are established, where the nonparametric functions achieve the optimal convergence rate and the parametric components are asymptotically normal even when the number of parameters in the linear part is diverging. We also propose a variable selection procedure based on penalization. Since the objective function is discontinuous, a practical estimation procedure is proposed using induced smoothing and we prove that the smoothed estimator is asymptotically equivalent to the original estimator. The proposed methods are evaluated via simulation studies and a real data application.
学科与关键词
- Estimation in quantile regression models for correlated data with diverging number of covariates and large cluster sizesZhao, Weihua; Zhang, Xiaoyu; Yuen, Kam Chuen; Li, Rui*; Lian, HengCOMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2023, 52(4): 1012-1038.
- Semiparametric penalized quadratic inference functions for longitudinal data in ultra-high dimensionsGreen, Brittany; Lian, Heng; Yu, Yan*; Zu, TianhaiJournal of Multivariate Analysis, 2023, 196: 105175.
- Partially functional linear quantile regression model and variable selection with censoring indicators MARWu, Chengxin; Ling, Nengxiang*; Vieu, Philippe; Liang, WenjuanJournal of Multivariate Analysis, 2023, 197: 105189.被引 2
