Health Equity Implications of Missing Data Among Youths With Childhood‐Onset Systemic Lupus Erythematosus: A Proof‐of‐Concept Study in the Childhood Arthritis and Rheumatology Research Alliance Registry
Main finding · Missing dataResult — go to the resultOdds ratio 2.04 95% CI 1.22–3.41Authors' conclusion
Our results support intentional evaluation of missing data to inform effect estimate interpretation and critical assessment of causal statements that might otherwise misrepresent health inequities.
Study context
- Population
- Participants with childhood-onset systemic lupus erythematosus (SLE) in the CARRA Registry, enrollment data 2015–2022
- Participants
- 766 participants
- Exposure
- Government-assisted vs private health insurance
- Outcome
- Missing data (co-missingness of 12 variables) and missing disease-related indices (SLEDAI-2K and/or SDI) at enrollment
- Follow-up
- Enrollment
Methodological detailsproof-of-concept, logistic regression, linear regression, complete case analysis, multiple imputation and nonprobabilistic bias analyses
- Proof-of-concept
- Logistic regression
- Linear regression
- Complete case analysis, multiple imputation and nonprobabilistic bias analyses
Main finding
Missing data
Odds ratio
2.04
95% CI 1.22–3.41
Government-assisted health insurancevs Private health insurance
OR 2.04 (95% CI 1.22–3.41)
As reported in the abstract
- Average proportion of data missing per participant
- 6.2%
- Participants missing at least 1 variable
- over 50%
Observational data: associations, not effects.
Further findings
Association between socioeconomic factors and SLEDAI-2K at enrollment by missing-data method
- Different analytic approaches gave varying analytic sample sizes and fundamentally conflicting estimated associations
Original publication
Health Equity Implications of Missing Data Among Youths With Childhood‐Onset Systemic Lupus Erythematosus: A Proof‐of‐Concept Study in the Childhood Arthritis and Rheumatology Research Alliance Registry. Arthritis Care Res (Hoboken). Published 30 May 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →