High-dimensional simultaneous inference with the bootstrap
High-dimensional simultaneous inference with the bootstrap
复制标题
DOI：
10.1007/s11749-017-0554-2
复制
发表时间：
2017-12-01
期刊：
影响因子：
1.3
通讯作者：
Zhang, Cun-Hui
中科院分区：
文献类型：
--
作者：
Dezeure, Ruben;Buhlmann, Peter;Zhang, Cun-Hui
我们提出了一种残差和野生自助方法，用于高维线性模型中可能存在非高斯和异方差误差的个体和同时推断。我们建立渐近一致性的参数同时推断组G，其中，和，p的变量的数量，n的样本大小和稀疏性。该理论得到了许多实证结果的补充。我们提出的程序在R包hdi中实现（Meier等人hdi：高维推理。R包版本0.1-6，2016）。
We propose a residual and wild bootstrap methodology for individual and simultaneous inference in high-dimensional linear models with possibly non-Gaussian and heteroscedastic errors. We establish asymptotic consistency for simultaneous inference for parameters in groups G, where , and , with p the number of variables, n the sample size and the sparsity. The theory is complemented by many empirical results. Our proposed procedures are implemented in the R-package hdi (Meier et al. hdi: high-dimensional inference. R package version 0.1-6, 2016).