Fig. 5From: Multiple imputation for patient reported outcome measures in randomised controlled trials: advantages and disadvantages of imputing at the item, subscale or composite score levelRMSE in the treatment effect estimates using the imputed OKS composite scores as the outcome variable in the regression model (observed missing data pattern). Abbreviations: CCA – Complete cases analysis; MAR – Missing at random; MI – Multiple imputation; OKS – Oxford knee score; PMM – Predicted mean matching; RMSE – Root mean square errorBack to article page