Evaluating patterns of inconsistent and missing data on the eating disorders examination-questionnaire in a sample of treatment-seeking adults and adolescents

Abstract

ABSTRACT Missing or inconsistent responses on self-report assessments can have implications for the use of empirically validated measurements in research and clinical practice. However, literature on frequency and systematic patterns of missingness on common measures of eating pathology is lacking. The current study evaluated EDE-Q missing and inconsistent responding in a clinical eating disorders (EDs) sample (N = 739). Thirteen percent (13.4%; n = 99) of the sample failed to provide complete responses on the EDE-Q and 13.8% (n = 101) inconsistently responded to behavioral items of the EDE-Q. Males were more likely to provide missing data, and mean BMI was higher among individuals with missing responses. Inconsistent responders endorsed higher scores on several EDE-Q subscales, were younger, and were more likely to be Hispanic/Latinx. However, many of these differences were not significant following correction for multiple comparisons. Although our results indicated similar rates of missingness and inconsistency to past work in college samples, our results suggest that missing and inconsistent responding on the EDE-Q in clinical samples may not warrant specialized consideration within statistical analyses.