Moderated regression analysis and Likert scales: Too coarse for comfort.

TLDR

The simple moderator effect is widely used in industrial and organizational psychology, yet empirical support for reported interaction effects is often questioned. The study proposes alternative research strategies to address these concerns. Using a continuous dependent-response scale instead of a discrete Likert scale increased moderated regression effect sizes by an average of 93%, indicating that coarse Likert scales cause information loss that markedly reduces the likelihood of detecting true interaction effects.

Abstract

One of the most commonly accepted models of relationships among three variables in applied industrial and organizational psychology is the simple moderator effect. However, many authors have expressed concern over the general lack of empirical support for interaction effects reported in the literature. We demonstrate in the current sample that use of a continuous, dependent-response scale instead of a discrete, Likert-type scale, causes moderated regression analysis effect sizes to increase an average of 93%. We suggest that use of relatively coarse Likert scales to measure fine dependent responses causes information loss that, although varying widely across subjects, greatly reduces the probability of detecting true interaction effects. Specific recommendations for alternate research strategies are made.