Detecting Interaction Effects in Moderated Multiple Regression With Continuous Variables Power and Sample Size Considerations
针对连续变量调节多重回归中交互效应难以检测的问题，提出一个统一框架来计算统计检验力和确定样本量，并通过数值模拟验证了方法的准确性。
In view of the long-recognized difficulties in detecting interactions among continuous variables in moderated multiple regression analysis, this article aims to address the problem by providing feasible solutions to power calculation and sample size determination for significance test of moderating effects. The proposed approach incorporates the essential factors of strength of moderator effect, magnitude of error variation, and distributional property of predictor and moderator variables into a unified framework. Accordingly, careful consideration across different plausible and practical configurations of the prescribed factors is an important aspect of power and sample size computations in planning moderated multiple regression research. The performance of the suggested procedure and an alternative simplified method is illustrated with detailed numerical studies. The simulation results demonstrate that an acceptable degree of accuracy can be obtained using the recommended method in assessing moderated relationships.