Which practice helps address missing data when evaluating equity in QI?

• A. Deleting all records with missing data
• B. Ignoring missing data
• C. Imputation strategies and sensitivity analyses
• D. Only analyze complete cases

Answer: (C)

Handling missing data properly is crucial when evaluating equity in quality improvement, because missingness can be related to group characteristics or outcomes and bias comparisons. When data are not missing completely at random, deleting records or analyzing only complete cases can distort apparent differences between groups and mask true inequities. Imputation strategies use the information we do have to fill in plausible values for missing entries, preserving sample size and the relationships among variables. Methods like multiple imputation create several complete datasets that reflect uncertainty about the missing values, and results are combined to give more accurate estimates and standard errors for subgroup comparisons. Sensitivity analyses then test how conclusions shift under different assumptions about why data are missing (for example, whether missingness is related to the outcome or to group membership). If the findings stay similar across reasonable scenarios, we can be more confident that the observed equity patterns reflect reality rather than data gaps. In short, imputation plus sensitivity analyses address missing data by reducing bias and evaluating robustness, whereas simply deleting data or ignoring missingness would likely misrepresent equity.