Normative Data Accounting for Multiple Qualitative and/or Quantitative Independent Variables

In the preceding chapters, the focus was on establishing regression-based normative data that account for a single independent variable. In practice, it often occurs that several independent variables have to be considered in a normative analysis (e.g., Age, Gender, and/or Level of Education). This chapter focuses on such settings. The general multiple linear regression model is introduced, and the important distinction between additive and interaction models is discussed. Furthermore, the relevance of the principle of marginality in a normative data context is stressed. This principle states that interaction models should always include the main effects that comprise a significant interaction term. The methodology for deriving norms that account for multiple independent variables is illustrated using the same two case studies as those that were analyzed in Chap. 6 . Here, the impact of Age, Gender, and Level of Education on the Letter Digit Substitution Test and the Total Recall Verbal Learning Test scores is examined, and normative data that account for the impact of the significant independent variables are provided. The analyses are conducted using the NormData package in the R software.