On the use of likert-type scales in multilevel data:Influence on aggregate variables

Beal, Daniel J. and Dawson, Jeremy F. (2007). On the use of likert-type scales in multilevel data:Influence on aggregate variables. Organizational Research Methods, 10 (4), pp. 657-672.

Abstract

In multilevel analyses, problems may arise when using Likert-type scales at the lowest level of analysis. Specifically, increases in variance should lead to greater censoring for the groups whose true scores fall at either end of the distribution. The current study used simulation methods to examine the influence of single-item Likert-type scale usage on ICC(1), ICC(2), and group-level correlations. Results revealed substantial underestimation of ICC(1) when using Likert-type scales with common response formats (e.g., 5 points). ICC(2) and group-level correlations were also underestimated, but to a lesser extent. Finally, the magnitude of underestimation was driven in large part to an interaction between Likert-type scale usage and the amounts of within- and between-group variance. © Sage Publications.

Publication DOI: https://doi.org/10.1177/1094428106295492
Divisions: Aston Business School > Work & organisational psychology
Uncontrolled Keywords: aggregation,intraclass correlation,Likert-type scale,Monte Carlo,multilevel,Management of Technology and Innovation,Strategy and Management,Decision Sciences(all)
Published Date: 2007-10

Download

Full text not available from this repository.

Export / Share Citation


Statistics

Additional statistics for this record