Non-asymptotic Analysis for Nonparametric Testing

Non-asymptotic Analysis for Nonparametric Testing
复制标题

DOI:
--
复制
发表时间:
2020-07
期刊:
arXiv: Statistics Theory
影响因子:
--
通讯作者:
Yun Yang;Zuofeng Shang;Guang Cheng
Yun Yang;Zuofeng Shang;Guang Cheng
中科院分区:
其他
文献类型:
--
作者:
Yun Yang;Zuofeng Shang;Guang Cheng

文献摘要

被引文献

相似文献

我们开发了一个非渐近的框架,在非参数回归的假设检验,真正的回归函数属于一个Sobolev空间。我们的统计保证是准确的,因为对于任何有限的样本量,I型和II型误差都是受控的。同时,一个建议的测试,以实现极大极小率最优的渐近意义。这个非渐近理论的一个重要结果是一个新的和实际有用的公式,用于选择最佳的平滑参数的检验统计量。我们的结果一般再生核希尔伯特空间和非高斯误差回归的扩展进行了讨论。
We develop a non-asymptotic framework for hypothesis testing in nonparametric regression where the true regression function belongs to a Sobolev space. Our statistical guarantees are exact in the sense that Type I and II errors are controlled for any finite sample size. Meanwhile, one proposed test is shown to achieve minimax rate optimality in the asymptotic sense. An important consequence of this non-asymptotic theory is a new and practically useful formula for selecting the optimal smoothing parameter in the testing statistic. Extensions of our results to general reproducing kernel Hilbert spaces and non-Gaussian error regression are also discussed.