Exponential regression for censored data with outliers
Exponential regression for censored data with outliers
复制标题
DOI：
10.1080/00949655.2015.1016432
复制
发表时间：
2016-02
影响因子：
1.2
通讯作者：
Jing Zhang;Yanyan Liu;Yuanshan Wu
中科院分区：
文献类型：
--
作者：
Jing Zhang;Yanyan Liu;Yuanshan Wu
我们提出了一种惩罚似然方法来检测指数回归模型中可能的异常值，同时利用它来拟合截尾生存数据。该方法可以同时处理异常值检测和回归系数估计。我们将异常点检测问题转化为一个高维正则化回归问题，并采用坐标下降算法来简化计算。大量的仿真研究和一个实例表明，该方法在指数回归模型的异常值检测和参数估计方面都有很好的效果。
We propose a penalized likelihood method to detect the possible outliers in the exponential regression model while it is utilized to fit the censored survival data. It features that the proposed method can simultaneously cope with outlier detection and estimation for the regression coefficient. We recast the outlier detection issue into a high-dimensional regularization regression and employ the coordinate descent algorithm to facilitate the computation. From both extensive simulation studies and an illustrative real example, it is shown that the proposed method works quite well in outlier detection as well as parameter estimation for the exponential regression model.