Which is a data quality issue that QA should address in behavior-change data collection?

• A. Missing Data
• B. Measurement Error
• C. Inconsistent Protocols
• D. All of the Above

Answer: (D)

In behavior-change data collection, QA focuses on ensuring data is complete, accurate, and collected consistently across observers and sites. Missing data reduces representativeness and statistical power, making analyses biased or less reliable. Addressing this involves monitoring data completeness, following up with participants, designing forms to minimize missing responses, and planning appropriate imputation or analysis strategies for leftover gaps.

Measurement error undermines accuracy because instruments can be faulty or participants may misreport behaviors due to recall or social desirability. QA helps by using validated measures, calibrating tools, training data collectors thoroughly, opting for objective measures when possible, and performing rigorous data cleaning and verification.

Inconsistent protocols cause variability that isn’t about the behavior itself but how data are collected. This is managed through standardized procedures, scripted data-collection prompts, comprehensive training, and regular audits or inter-rater reliability checks to ensure uniform application.

Since missing data, measurement error, and inconsistent protocols are all quality problems that can distort findings, QA should address all of them. That makes “All of the above” the best answer.