Skip to main content
Fig. 2 | Health and Quality of Life Outcomes

Fig. 2

From: Practical issues encountered while determining Minimal Clinically Important Difference in Patient-Reported Outcomes

Fig. 2

Illustration of the imputation methods used. MD Missing data. X completed item; MICE Multivariate Imputation with Chained Equations. 1PMS Personal Mean Score : each item is imputed 2Missing data in scores were imputed by the mean of observed scores ; missing data in anchor were imputed using a random sample weighted with observed probabilities of answers at corresponding anchor. 3Missing scores were imputed using personal mean matching, missing anchors were imputed using a polytomous regression, both using clinical and demographic variables. 4Missing scores were imputed using personal mean matching, missing anchors were imputed using a polytomous regression, both using clinical and demographic variables, and all scores from other dimensions

Back to article page