| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 1151543 | Statistics & Probability Letters | 2016 | 9 Pages |
Abstract
By incorporating the Expectation–maximization (EM) algorithm into composite asymmetric Laplace distribution (CALD), an iterative weighted least square estimator for the linear composite quantile regression (CQR) models is derived. Two selection methods for the number of composite quantiles via redefined AIC and BIC are developed. Finally, the proposed procedures are illustrated by some simulations.
Related Topics
Physical Sciences and Engineering
Mathematics
Statistics and Probability
Authors
Yuzhu Tian, Qianqian Zhu, Maozai Tian,