Block average quantile regression for massive dataset

Nowadays, researchers are frequently confronted with challenges from large-scale data computing. Quantile regression on massive dataset is challenging due to the limitations of computer primary memory. Our proposed block average quantile regression provides a simple and efficient way to implement qu...

Full description

Saved in:
Bibliographic Details
Published in:Statistical papers (Berlin, Germany) Germany), 2020-02, Vol.61 (1), p.141-165
Main Authors: Xu, Qifa, Cai, Chao, Jiang, Cuixia, Sun, Fang, Huang, Xue
Format: Article
Language:English
Subjects:
Adultery
Asymptotic properties
Computer simulation
Datasets
Economic models
Economic Theory/Quantitative Economics/Mathematical Methods
Economics
Finance
Forecasting techniques
Insurance
Management
Mathematics and Statistics
Monte Carlo simulation
Normal distribution
Operations Research/Decision Theory
Probability Theory and Stochastic Processes
Regression
Regular Article
Statistical analysis
Statistics
Statistics for Business
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Nowadays, researchers are frequently confronted with challenges from large-scale data computing. Quantile regression on massive dataset is challenging due to the limitations of computer primary memory. Our proposed block average quantile regression provides a simple and efficient way to implement quantile regression on massive dataset. The major novelty of this method is splitting the entire data into a few blocks, applying the convectional quantile regression onto the data within each block, and deriving final results through aggregating these quantile regression results via simple average approach. While our approach can significantly reduce the storage volume needed for estimation, the resulting estimator is theoretically as efficient as the traditional quantile regression on entire dataset. On the statistical side, asymptotic properties of the resulting estimator are investigated. We verify and illustrate our proposed method via extensive Monte Carlo simulation studies as well as a real-world application.
ISSN:0932-5026
1613-9798
DOI:10.1007/s00362-017-0932-6