Tests alternative to higher criticism for high-dimensional means under sparsity and column-wise dependence

Tests alternative to higher criticism for high-dimensional means under sparsity and column-wise dependence
复制标题

在稀疏性和列相关性下测试高维手段的更高批评的替代方案

DOI:
10.1214/13-aos1168
复制
发表时间:
2013-12
影响因子:
4.5
通讯作者:
Xu Minya
Xu Minya
中科院分区:
数学1区
文献类型:
--
作者:
Zhong Ping-Shou;Chen Song Xi;Xu Minya

文献摘要

参考文献

被引文献

相似文献

我们认为两个替代测试的更高的批评测试多诺霍和金[安。32(2004)962-994]中描述的方法。这两个替代的测试统计量是通过第一阈值$L_1$和$L_2$统计的样本均值的基础上,分别,然后通过最大化的阈值水平的范围内,使测试适应未知的信号强度和稀疏性。这两个替代检验可以达到与[Ann. Statistist. 32(2004)962-994],其针对不相关的高斯数据建立。证明了最大L_2 $-阈值检验至少与最大L_1 $-阈值检验一样有效,最大L_2 $和L_1 $-阈值检验至少与Higher Criticism检验一样有效。
We consider two alternative tests to the Higher Criticism test of Donoho and Jin [Ann. Statist. 32 (2004) 962-994] for high-dimensional means under the sparsity of the nonzero means for sub-Gaussian distributed data with unknown column-wise dependence. The two alternative test statistics are constructed by first thresholding $L_1$ and $L_2$ statistics based on the sample means, respectively, followed by maximizing over a range of thresholding levels to make the tests adaptive to the unknown signal strength and sparsity. The two alternative tests can attain the same detection boundary of the Higher Criticism test in [Ann. Statist. 32 (2004) 962-994] which was established for uncorrelated Gaussian data. It is demonstrated that the maximal $L_2$-thresholding test is at least as powerful as the maximal $L_1$-thresholding test, and both the maximal $L_2$ and $L_1$-thresholding tests are at least as powerful as the Higher Criticism test.
DOI: 10.1214/aop/1024404289
发表时间: 1997
影响因子: 2.3
作者:
Q. Shao
通讯作者: Q. Shao
DOI: 10.1007/978-1-4757-2545-2
发表时间: 1996-03
期刊: --
影响因子: --
作者:
T. Mikosch;A. Vaart;J. Wellner
通讯作者: T. Mikosch;A. Vaart;J. Wellner
DOI: 10.1090/s0002-9947-08-04402-4
发表时间: 2008-03
影响因子: 1.3
作者:
Bing-Yi Jing;Q. Shao;Wang Zhou
通讯作者: Bing-Yi Jing;Q. Shao;Wang Zhou
DOI: 10.1214/11-aos964
发表时间: 2011-06
影响因子: 4.5
作者:
E. Arias-Castro;Sébastien Bubeck;G. Lugosi
通讯作者: E. Arias-Castro;Sébastien Bubeck;G. Lugosi
DOI: 10.3150/13-bej565
发表时间: 2012-02
期刊: Bernoulli
影响因子: 1.5
作者:
E. Arias-Castro;Sébastien Bubeck;G. Lugosi
通讯作者: E. Arias-Castro;Sébastien Bubeck;G. Lugosi