Inclusion of Careless Respondents on Factor Analytic Results: Investigation With Real Data

• In Event: Roundtable Session 14
  In Roundtable Session: Effects of Aberrant Response Patterns on Test Scores

Abstract

This study is to investigate the impact of careless responding on factor analytic results with real data. Survey data with 666 respondents showed that careless responding weakened factor correlation between regular- and reverse-keyed items. Acquiescence bias, i.e., consistent agreement (or disagreement) with survey items regardless of item content, was also found to be stronger among the careless group as compared to the careful group. The statistical method to control for acquiescence bias turned the moderately negative factor correlation between job satisfaction and dissatisfaction to become a nearly perfect negative correlation among careful respondents. Results suggest researchers to identify careless respondents and control for acquiescence bias. Inclusion of careless respondents clearly distorts factor correlation in the present data.

Authors

• Chun Seng Kam, University of Macau

• John P. Meyer