Tuning parameter selectors for the smoothly clipped absolute deviation method
Tuning parameter selectors for the smoothly clipped absolute deviation method
复制标题
DOI：
10.1093/biomet/asm053
复制
发表时间：
2007-08-01
期刊：
影响因子：
2.7
通讯作者：
Tsai, Chih-Ling
中科院分区：
文献类型：
--
作者：
Wang, Hansheng;Li, Runze;Tsai, Chih-Ling
具有平滑剪裁绝对偏差惩罚的惩罚最小二乘方法已被一致证明是一种有吸引力的回归收缩和选择方法。它不仅自动一致地选择重要变量，而且产生的估计器与oracle估计器一样高效。然而，这些吸引人的特性依赖于适当的调谐参数选择。结果表明，常用的广义交叉验证方法不能令人满意地选择调优参数，结果模型存在不可忽视的过拟合效应。此外，我们提出了一个BIC调优参数选择器，该选择器能够一致地识别真实模型。本文提出了仿真研究来支持理论发现，并给出了一个实证例子来说明其在女性劳动力供给数据中的应用。
The penalized least squares approach with smoothly clipped absolute deviation penalty has been consistently demonstrated to be an attractive regression shrinkage and selection method. It not only automatically and consistently selects the important variables, but also produces estimators which are as efficient as the oracle estimator. However, these attractive features depend on appropriate choice of the tuning parameter. We show that the commonly used generalized crossvalidation cannot select the tuning parameter satisfactorily, with a nonignorable overfitting effect in the resulting model. In addition, we propose a BIC tuning parameter selector, which is shown to be able to identify the true model consistently. Simulation studies are presented to support theoretical findings, and an empirical example is given to illustrate its use in the Female Labor Supply data.