Model selection consistency of Dantzig selector
Model selection consistency of Dantzig selector
复制标题
DOI：
10.5705/ss.2012.061
复制
发表时间：
2013
影响因子：
1.4
通讯作者：
G. Yu-jie;Li-Xing Zhu;Lin Lu
中科院分区：
文献类型：
--
作者：
G. Yu-jie;Li-Xing Zhu;Lin Lu
: Consistency of model selection hinges on the correlation between significant and insignificant predictors for “large p , small n ” problems. Thus, Ir-representable Conditions play an important role in consistency, that insignificant predictors are irrepresentable by significant ones. In this paper, we provide Ir-representable Conditions when the Dantzig selector is applied; they ensure that the Dantzig selector consistently selects the true model with fixed p and diverging p (number of predictors) even at an exponential rate of n . Our conditions are sufficient for a strong sign consistency and Weak Irrepresentable Conditions are necessary for a weak sign consistency. Strong sign consistency leads to the conventional consistency of the estimation. As a by-product, the results also show the difference between the Dantzig selector and the Lasso when consistency is at issoe. Simulation studies are performed to examine the theoretical results.
