Data Quality in web-based HIV/AIDS research: Handling Invalid and Suspicious Data

Abstract

Invalid data may compromise data quality. We examined how decisions taken to handle these data may affect the relationship between Internet use and HIV risk behaviors in a sample of young men who have sex with men (YMSM). We recorded 548 entries during the three-month period, and created 6 analytic groups (i.e., full sample, entries initially tagged as valid, suspicious entries, valid cases mislabeled as suspicious, fraudulent data, and total valid cases) using data quality decisions. We compared these groups on the sample's composition and their bivariate relationships. Forty-one cases were marked as invalid, affecting the statistical precision of our estimates but not the relationships between variables. Sixty-two additional cases were flagged as suspicious entries and found to contribute to the sample's diversity and observed relationships. Using our final analytic sample (N = 447; M = 21.48 years old, SD = 1.98), we found that very conservative criteria regarding data exclusion may prevent researchers from observing true associations. We discuss the implications of data quality decisions and its implications for the design of future HIV/AIDS web-surveys.

Figure 1

Decomposition of the sample to ensure adequate final analytic sample Notes. Adjusted Completion rates are calculated taking full missing data out of the estimation. Completion rate = [488/548] = 89.05% Adjusted Completion Rate using Group A = [385/488] = 78.89% Adjusted Completion Rate using Group E = [447/488] = 91.60%