Nonparametric Independence Screening in Sparse Ultra-High Dimensional Additive Models.
Nonparametric Independence Screening in Sparse Ultra-High Dimensional Additive Models.
复制标题
DOI：
10.1198/jasa.2011.tm09779
复制
发表时间：
2011-06
影响因子：
3.7
通讯作者：
Song R
中科院分区：
文献类型：
--
作者：
Fan J;Feng Y;Song R
提出了通过相关学习的可变筛选程序，以降低稀疏超高维模型中的维度。即使真实模型是线性的，边缘回归也可以是高度非线性的。为了解决这个问题，我们将相关性学习进一步扩展到边际非参数学习。我们的非参数独立性筛选称为NIS，NIS是确定独立性筛选的特定成员。提出了几种密切相关的可变筛选程序。在一般的非参数模型下，表明在某些温和的技术条件下，拟议的独立筛选方法享有确定的筛选属性。独立筛选可以降低维度的程度，也被明确量化。作为方法论扩展，还提出了数据驱动的阈值和迭代非参数独立性筛选（INIS），以增强有限样本性能，以拟合稀疏的添加模型。仿真结果和实际数据分析表明，所提出的过程与中等样本量和较大维度很好，并且比竞争方法更好。
A variable screening procedure via correlation learning was proposed in to reduce dimensionality in sparse ultra-high dimensional models. Even when the true model is linear, the marginal regression can be highly nonlinear. To address this issue, we further extend the correlation learning to marginal nonparametric learning. Our nonparametric independence screening is called NIS, a specific member of the sure independence screening. Several closely related variable screening procedures are proposed. Under general nonparametric models, it is shown that under some mild technical conditions, the proposed independence screening methods enjoy a sure screening property. The extent to which the dimensionality can be reduced by independence screening is also explicitly quantified. As a methodological extension, a data-driven thresholding and an iterative nonparametric independence screening (INIS) are also proposed to enhance the finite sample performance for fitting sparse additive models. The simulation results and a real data analysis demonstrate that the proposed procedure works well with moderate sample size and large dimension and performs better than competing methods.
登录
查看更多内容
影响因子：
2.4
作者：
Hall, Peter;Miller, Hugh
通讯作者：
Miller, Hugh
影响因子：
1.5
作者：
Horowitz, J;Klemelä, J;Mammen, E
通讯作者：
Mammen, E
影响因子：
4.5
作者：
Huang J;Horowitz JL;Wei F
通讯作者：
Wei F
DOI：
10.1073/pnas.0600158103
发表时间：
2006-04-18
影响因子：
11.1
作者：
Chiang, AP;Beck, JS;Sheffield, VC
通讯作者：
Sheffield, VC
影响因子：
4.5
作者：
SILVERMAN, BW
通讯作者：
SILVERMAN, BW