THE IMPACT OF CONFOUNDER SELECTION CRITERIA ON EFFECT ESTIMATION
THE IMPACT OF CONFOUNDER SELECTION CRITERIA ON EFFECT ESTIMATION
复制标题
DOI：
10.1093/oxfordjournals.aje.a115101
复制
发表时间：
1989-01-01
影响因子：
5
通讯作者：
GREENLAND, S
中科院分区：
文献类型：
--
作者：
MICKEY, RM;GREENLAND, S
关于混杂因素控制中变量选择的正确方法存在很多争议。许多作者谴责任何显着性检验的使用，一些作者鼓励这种检验，还有一些作者提出了混合方法。本文介绍了几个混杂因素选择标准的蒙特卡罗模拟结果，包括估计变化和折叠性测试标准。比较这些方法对有关研究因素效果的推论的影响，通过测试规模和功效、偏倚均方误差和置信区间覆盖率来衡量。在最佳决策（是否调整）并不总是显而易见的情况下，估计变化标准往往更优越，但如果将显着性水平设置为远高于常规水平（达到 0.20 或更高的值），则显着性检验方法的表现可以接受。
Much controversy exists regarding proper methods for the selection of variables in confounder control. Many authors condemn any use of significance testing, some encourage such testing, and others propose a mixed approach. This paper presents the results of a Monte Carlo simulation of several confounder selection criteria, including change-in-estimate and collapsibility test criteria. The methods are compared with respect to their impact on inferences regarding the study factor''s effect, as measured by test size and power, bias mean-squared error, and confidence interval coverage rates. In situations in which the best decision (of whether or not to adjust) is not always obvious, the change-in-estimate criterion tends to be superior, though significance testing methods can perform acceptably if their significance levels are set much higher than conventional levels (to values of 0.20 or more).