Computational tools for probing interactions in multiple linear regression, multilevel modeling, and latent curve analysis
Computational tools for probing interactions in multiple linear regression, multilevel modeling, and latent curve analysis
复制标题
DOI：
10.3102/10769986031004437
复制
发表时间：
2006-12-01
影响因子：
2.4
通讯作者：
Bauer, Daniel J.
中科院分区：
文献类型：
--
作者：
Preacher, Kristopher J.;Curran, Patrick J.;Bauer, Daniel J.
在多元线性回归（MLR）模型中，简单斜率、显著性区域和置信带通常用于评估相互作用，这些技术的使用最近已扩展到多层或分层线性建模（HLM）和潜在曲线分析（LCA）。然而，执行这些测试和绘制条件关系通常是一项乏味且容易出错的任务。本文概述了用于探测相互作用效应的方法，并描述了一个免费的在线资源的统一集合，研究人员可以使用这些资源获得简单斜率的显著性检验，计算显著性区域，并获得MLR、HLM和LCA上下文中调节器范围内的简单斜率的置信带。还提供了绘图功能。
Simple slopes, regions of significance, and confidence bands are commonly used to evaluate interactions in multiple linear regression (MLR) models, and the use of these techniques has recently been extended to multilevel or hierarchical linear modeling (HLM) and latent curve analysis (LCA). However, conducting these tests and plotting the conditional relations is often a tedious and error-prone task. This article provides an overview of methods used to probe interaction effects and describes a unified collection of freely available online resources that researchers can use to obtain significance tests for simple slopes, compute regions of significance, and obtain confidence bands for simple slopes across the range of the moderator in the MLR, HLM, and LCA contexts. Plotting capabilities are also provided.