arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.08431stat.MEmath.STstat.COstat.TH
收藏

Wald检验中的Hauck-Donner效应:检测、临界点和参数空间特征

On the Hauck-Donner Effect in Wald Tests: Detection, Tipping Points, and Parameter Space Characterization

Thomas William Yee

摘要:

Wald检验在统计实践中仍然无处不在,尽管它存在一些缺点,如小样本的不准确性和重新参数化下的不变性。本文发展的另一个,但鲜为人知的缺点称为Hauck-唐纳效应(HDE),即沃尔德检验统计量不是单调增加的函数之间的距离增加的参数估计和零值。导致向上偏置的$p$值和功率损失,畸变可导致非常有害的后果,例如在变量选择中。HDE影响许多类型的回归模型,并对应于参数空间边界附近的估计。本文提出了几个新的结果,其主要贡献是:(i)提出了一个检测HDE的通用检验方法,而不管其根本原因是什么;(ii)用Wald和Rao得分的两两比和1-参数分布的似然比检验统计量从根本上刻画了HDE的特征;(iii)表明参数空间可以被划分成由5个HDE严重性度量包围的内部(微弱,弱,中等,强,极端);(iv)证明HDE在2 × 2表中的必要条件是对数比值比至少为2;(v)给出一些关于无HDE假设检验的实用指南。总体而言,现在可以对任何通过迭代重加权最小二乘估计的模型进行实际的拟合后检验,例如广义线性模型(GLM)和向量GLM(VGLM)类,后者包含许多流行的回归模型。

英文摘要:

The Wald test remains ubiquitous in statistical practice despite shortcomings such as its inaccuracy in small samples and lack of invariance under reparameterization. This paper develops on another but lesser-known shortcoming called the Hauck--Donner effect (HDE) whereby a Wald test statistic is not monotonely increasing as a function of increasing distance between the parameter estimate and the null value. Resulting in an upward biased $p$-value and loss of power, the aberration can lead to very damaging consequences such as in variable selection. The HDE afflicts many types of regression models and corresponds to estimates near the boundary of the parameter space. This article presents several new results, and its main contributions are to (i) propose a very general test for detecting the HDE, regardless of its underlying cause; (ii) fundamentally characterize the HDE by pairwise ratios of Wald and Rao score and likelihood ratio test statistics for 1-parameter distributions; (iii) show that the parameter space may be partitioned into an interior encased by 5 HDE severity measures (faint, weak, moderate, strong, extreme); (iv) prove that a necessary condition for the HDE in a 2 by 2 table is a log odds ratio of at least 2; (v) give some practical guidelines about HDE-free hypothesis testing. Overall, practical post-fit tests can now be conducted potentially to any model estimated by iteratively reweighted least squares, such as the generalized linear model (GLM) and Vector GLM (VGLM) classes, the latter which encompasses many popular regression models.

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。

↑