arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1512.03479math.STstat.TH
收藏

随机设计二元回归的最优自适应推断

Optimal Adaptive Inference in Random Design Binary Regression

Rajarshi Mukherjee, Subhabrata Sen

摘要:

我们在设计密度未知的非参数二元回归中为回归函数构造置信集。这些置信集是自适应的$L^2$损失的Sobolev型空间的连续类。自适应保持在回归函数的平滑性中,在自适应是可能的最大参数空间上,只要设计密度足够平滑。我们确定了两个关键制度-一个是适应是可能的,一个是一些临界区域必须删除。我们解决相关问题的拟合优度测试和自适应估计的相关参数。

英文摘要:

We construct confidence sets for the regression function in nonparametric binary regression with an unknown design density. These confidence sets are adaptive in $L^2$ loss over a continuous class of Sobolev type spaces. Adaptation holds in the smoothness of the regression function, over the maximal parameter spaces where adaptation is possible, provided the design density is smooth enough. We identify two key regimes --- one where adaptation is possible, and one where some critical regions must be removed. We address related questions about goodness of fit testing and adaptive estimation of relevant parameters.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑