Fig. 3From: Using random-forest multiple imputation to address bias of self-reported anthropometric measures, hypertension and hypercholesterolemia in the Belgian health interview surveyPrevalence estimates of overweight, obesity, hypertension and hypercholesterolemia in Belgium using self-reported, measured and adjusted 2018 BHIS data. Classical MI: classical multiple imputation. RF MI: random-forest multiple imputation. Regression calibration and multiple imputation model included age, sex, education level and the self-reported health conditions. Error bars represent one standard deviation of uncertainty of the estimatesBack to article page