Abstract
We apply the potential outcomes framework in the analysis of an observational study of rheumatoid arthritis patients, in which we compare the mean functional-health and well-being scores (SF-36) of patients who are overweight and who are not. We combine propensity score matching with multiple imputation for nonresponse. We assess the sensitivity of the conclusions with respect to the details of the propensity model and the definition of being overweight. © 2011 Springer Science+Business Media, LLC.
Original language | English |
---|---|
Pages (from-to) | 27-43 |
Journal | Health Services and Outcomes Research Methodology |
Volume | 11 |
DOIs | |
Publication status | Published - 1 Jul 2011 |
Keywords
- Body mass index
- Multiple imputation
- Potential outcomes
- Propensity score matching
- Rheumatoid arthritis