Solutions for Determining the Significance Region Using the Johnson-Neyman Type Procedure in Generalized Linear (Mixed) Models.

Solutions for Determining the Significance Region Using the Johnson-Neyman Type Procedure in Generalized Linear (Mixed) Models.
复制标题

DOI:
10.3102/1076998610396889
复制
发表时间:
2011-12
期刊:
Journal of educational and behavioral statistics : a quarterly publication sponsored by the American Educational Research Association and the American Statistical Association
影响因子:
--
通讯作者:
Zerbe GO
Zerbe GO
中科院分区:
其他
文献类型:
--
作者:
Lazar AA;Zerbe GO

文献摘要

参考文献

被引文献

相似文献

研究人员经常通过评估拟合回归曲线是否存在显著差异,来比较两个或多个组中结果与协变量之间的关系。当存在差异时,研究人员需要确定“显著区域”,即曲线存在显著差异的协变量的值。在协方差分析(ANCOVA)中,可使用约翰逊 - 奈曼(Johnson - Neyman)方法来确定显著区域;对于分层线性模型(HLM),有人建议使用宫崎和迈尔(Miyazaki and Maier,M - M)方法。然而,这两种方法都不能假定数据呈非正态分布。此外,M - M方法会产生有偏(向下)的结果,因为它使用了沃尔德检验,无法控制由于多次检验导致的第一类错误率膨胀,并且需要使用多个软件包来确定显著区域。在本文中,我们针对这些局限性提出了适用于广义线性(混合)模型(GLM或GLMM)的确定显著区域的解决方案。这些提出的解决方案包含能解决有偏结果的检验统计量,使用谢弗方法控制第一类错误率,并使用单个统计软件包来确定显著区域。
Researchers often compare the relationship between an outcome and covariate for two or more groups by evaluating whether the fitted regression curves differ significantly. When they do, researchers need to determine the “significance region,” or the values of the covariate where the curves significantly differ. In analysis of covariance (ANCOVA), the Johnson-Neyman procedure can be used to determine the significance region; for the hierarchical linear model (HLM), the Miyazaki and Maier (M-M) procedure has been suggested. However, neither procedure can assume nonnormally distributed data. Furthermore, the M-M procedure produces biased (downward) results because it uses the Wald test, does not control the inflated Type I error rate due to multiple testing, and requires implementing multiple software packages to determine the significance region. In this article, we address these limitations by proposing solutions for determining the significance region suitable for generalized linear (mixed) model (GLM or GLMM). These proposed solutions incorporate test statistics that resolve the biased results, control the Type I error rate using Scheffé’s method, and uses a single statistical software package to determine the significance region.
DOI: 10.2307/2287835
发表时间: 1981-01-01
影响因子: 3.7
作者:
DEMPSTER, AP;RUBIN, DB;TSUTAKAWA, RK
通讯作者: TSUTAKAWA, RK
DOI: 10.2307/1165228
发表时间: 1997-12-01
影响因子: 2.4
作者:
Hunka, S;Leighton, J
通讯作者: Leighton, J
DOI: 10.1111/j.2044-8317.1995.tb01056.x
发表时间: 1995-05-01
影响因子: 2.6
作者:
HUNKA, S
通讯作者: HUNKA, S
DOI: 10.1007/bf02289721
发表时间: 1964-01-01
期刊: PSYCHOMETRIKA
影响因子: 3
作者:
POTTHOFF, RF
通讯作者: POTTHOFF, RF
DOI: 10.3102/10769986030003233
发表时间: 2005-09-01
影响因子: 2.4
作者:
Miyazaki, Y;Maier, KS
通讯作者: Maier, KS