Quantile regression shrinkage and selection via the Lqsso

被引:3
作者
Daneshvar, Alireza [1 ]
Golalizadeh, Mousa [1 ]
机构
[1] Tarbiat Modares Univ, Dept Stat, Tehran, Iran
关键词
Quantile regression; shrinkage; oracle property; consistency; lasso; VARIABLE SELECTION; ADAPTIVE LASSO; ASYMPTOTICS;
D O I
10.1080/10543406.2023.2198593
中图分类号
R9 [药学];
学科分类号
1007 ;
摘要
Quantile regression has recently received a considerable attention due to its remarkable development in enriching the variety of regression models. Many efforts have been made to blend different penalty and loss function to extend or develop novel regression models that are unique from different perspectives. Bearing in mind that the lasso quantile regression model ignores the randomness of the realizations in the penalty part, we propose a new penalty for the quantile regression models. Similar to the adaptive lasso quantile regression model, the proposed model simultaneously does estimation and variable selection tasks. We call the new model 'lqsso-QR', standing for the least quantile shrinkage and selection operator quantile regression. In this article, we present a sufficient and necessary condition for the variable selection of the lasso quantile regression to enjoy the consistent property. We show that the lqsso-QR follows oracle properties under some mild conditions. From computational perspective, we apply an efficient algorithm, originally developed for the lasso quantile regression. Using simulation studies, we elaborate on the superiority of the proposed model compared with other lasso-type penalties, especially regarding relative prediction error. Also, an application of our method to a real-life data; the rat eye data, is reported.
引用
收藏
页码:297 / 322
页数:26
相关论文
共 50 条
[31]   Variable selection of the quantile varying coefficient regression models [J].
Zhao, Weihua ;
Zhang, Riquan ;
Lv, Yazhao ;
Liu, Jicai .
JOURNAL OF THE KOREAN STATISTICAL SOCIETY, 2013, 42 (03) :343-358
[32]   Simultaneous variable selection and parametric estimation for quantile regression [J].
Wei Xiong ;
Maozai Tian .
Journal of the Korean Statistical Society, 2015, 44 :134-149
[33]   Quantile regression and variable selection of partial linear single-index model [J].
Lv, Yazhao ;
Zhang, Riquan ;
Zhao, Weihua ;
Liu, Jicai .
ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 2015, 67 (02) :375-409
[34]   Model selection in quantile regression models [J].
Alhamzawi, Rahim .
JOURNAL OF APPLIED STATISTICS, 2015, 42 (02) :445-458
[35]   FOCUSSED MODEL SELECTION IN QUANTILE REGRESSION [J].
Behl, Peter ;
Claeskens, Gerda ;
Dette, Holger .
STATISTICA SINICA, 2014, 24 (02) :601-624
[36]   Feature selection for probabilistic load forecasting via sparse penalized quantile regression [J].
Wang, Yi ;
Gan, Dahua ;
Zhang, Ning ;
Xie, Le ;
Kang, Chongqing .
JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY, 2019, 7 (05) :1200-1209
[37]   Modified check loss for efficient estimation via model selection in quantile regression [J].
Jung, Yoonsuh ;
MacEachern, Steven N. ;
Kim, Hang .
JOURNAL OF APPLIED STATISTICS, 2021, 48 (05) :866-886
[38]   Variable selection via quantile regression with the process of Ornstein-Uhlenbeck type [J].
Yinfeng Wang ;
Xinsheng Zhang .
Science China Mathematics, 2022, 65 :827-848
[39]   Gene selection for microarray gene expression classification using Bayesian Lasso quantile regression [J].
Algamal, Zakariya Yahya ;
Alhamzawi, Rahim ;
Ali, Haithem Taha Mohammad .
COMPUTERS IN BIOLOGY AND MEDICINE, 2018, 97 :145-152
[40]   Variable selection in competing risks models based on quantile regression [J].
Li, Erqian ;
Tian, Maozai ;
Tang, Man-Lai .
STATISTICS IN MEDICINE, 2019, 38 (23) :4670-4685