A novel method for modelling interaction between categorical variables
A novel method for modelling interaction between categorical variables
复制标题
DOI：
10.1007/s00038-016-0902-0
复制
发表时间：
2017-04-01
影响因子：
4.6
通讯作者：
Konig, Ruben
中科院分区：
文献类型：
--
作者：
te Grotenhuis, Manfred;Pelzer, Ben;Konig, Ruben
Sweeney和Ulveling（1972）引入了加权效应编码，其中名义型和有序型变量类别的估计值是算术平均值的偏差，通常来自样本。如果数据不平衡（即，当类别包含不同数量的观察值时），这种稍微被忽视的参数化优于众所周知的效应编码（ANOVA），并且最近在该杂志上恢复（te Grotenhuis等人。2016）。在本文中，我们证明了加权效应编码也可以应用于具有交互效应的回归模型。加权效应编码的交互作用表示从不含这些交互作用的模型中获得的主效应之上的附加效应。这是一个有用的替代效果编码时，数据是不平衡的，在大多数观测数据。在这篇文章中，我们描述了这种新的参数化，并提供了语法，数据和例子在SPSS，R和Stata在http：//www。茹nl/sociology/mt/wec/downloads.出于教学原因，我们应用OLS回归模型，但加权效应编码的相互作用可以用于任何广义线性模型。在本文中，我们使用“相互作用”这个词，而其他研究人员更喜欢“适度”。
Sweeney and Ulveling (1972) introduced weighted effect coding, where the estimates for categories of nominal and ordinal variables are deviations from the arithmetic mean, typically from a sample. This somewhat neglected parameterization is preferred over the well-known effect coding (ANOVA) if the data are unbalanced (ie, when categories hold different numbers of observations) and was recently revived in this journal (te Grotenhuis et al. 2016). In this paper, we show that weighted effect coding can also be applied to regression models with interaction effects. The weighted effect coded interactions represent the additional effects over and above the main effects obtained from the model without these interactions. This is a useful alternative to effect coding when the data are unbalanced as in most observational data. In this contribution, we describe this novel parameterization and provide syntax, data, and examples in SPSS, R, and Stata on http://www. ru. nl/sociology/mt/wec/downloads. For didactical reasons we apply OLS regression models, but weighted effect coded interactions can be used in any generalized linear model. Throughout this text we use the word ‘interaction’, while other researchers prefer ‘moderation’.