arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.05056stat.ME
收藏

高维Newey-Powell检验与近似消息传递

High-dimensional Newey-Powell Test Via Approximate Message Passing

University of Manchester(曼彻斯特大学);University of Minnesota Twin Cities(明尼苏达大学双城分校)

Jing Zhou, Hui Zou

AI总结:

本文提出一种高维异方差性检验方法,基于近似消息传递算法,通过模拟和实际数据验证其有效性。

摘要:

我们提出了一种高维异方差性检验的扩展,该检验基于比例渐近 regime 中的 expectile 回归,其中 n/p → δ ∈ (0,1]。检验统计量的渐近分析使用了近似消息传递(AMP)算法,从而得到检验的极限分布并建立其渐近功效。通过广泛的模拟研究验证了检验的数值性能。作为实际数据应用,我们基于“国际经济增长”数据(Belloni 等,2011)进行分析,发现其为同方差性;基于“超市”数据(Lan 等,2016)进行分析,发现其为异方差性。

英文摘要:

We propose a high-dimensional extension of the heteroscedasticity test proposed in Newey and Powell (1987). Our test is based on expectile regression in the proportional asymptotic regime where n/p \to δ\in (0,1]. The asymptotic analysis of the test statistic uses the Approximate Message Passing (AMP) algorithm, from which we obtain the limiting distribution of the test and establish its asymptotic power. The numerical performance of the test is validated through an extensive simulation study. As real-data applications, we present the analysis based on ``international economic growth" data (Belloni et al., 2011), which is found to be homoscedastic, and ``supermarket" data (Lan et al., 2016), which is found to be heteroscedastic.

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。

↑