Detecting Social Desirability Bias Using Factor Mixture Models

摘要: Based on the conceptualization that social desirable bias (SDB) is a discrete event resulting from an interaction between scale's items, testing situation, and respondent's latent trait desirability factor, we present method makes use of factor mixture models to identify which examinees are most likely provide biased responses, items elicit socially external variables predict SDB. Problems associated with common correlation coefficients based scales' total scores diagnose SDB partial correlations correct for discussed. The demonstrated analysis in Attitude toward Interprofessional Service-Learning scale sample students health-related fields.