A note on estimating the bent line quantile regression model
A note on estimating the bent line quantile regression model
复制标题
DOI：
10.1007/s00180-017-0711-9
复制
发表时间：
2017-02
影响因子：
1.3
通讯作者：
Yanyang Yan;Feipeng Zhang;Xiaoying Zhou
中科院分区：
文献类型：
--
作者：
Yanyang Yan;Feipeng Zhang;Xiaoying Zhou
本文考虑了一种新的折线分位数回归模型估计方法。通过简单的线性化技术，所提出的方法可以同时获得回归系数和变化点位置的估计。此外，它可以很容易地通过当前的软件来实现。仿真研究表明该方法具有良好的有限样本性能。还提出了两个实证应用来说明该方法。
This paper considers a new estimating method for the bent line quantile regression model. By a simple linearization technique, the proposed method can simultaneously obtain the estimates of the regression coefficients and the change-point location. Moreover, it can be readily implemented by current software. Simulation studies demonstrate that the proposed method has good finite sample performance. Two empirical applications are also presented to illustrate the method.