Skip to main content
. Author manuscript; available in PMC: 2015 Feb 10.
Published in final edited form as: Stat Med. 2013 Aug 11;33(3):401–421. doi: 10.1002/sim.5937

Figure 5.

Figure 5

Equal proportion of missing data in predictors M1 and equal prevalence of cases and non-cases in the training data set: performance of the methods with respect to misclassification error and area under the receiver operating characteristic curve (AUC) in the test data set under the six scenarios C1 to C6. RF refers to Random Forest; RF10 refers to Random Forest with 10 variables selected; ElNet refers to Elastic Net; ImpLas refers to Imputed-LASSO. Note: Random Forest should not be compared with other methods.