Skip to main content
. Author manuscript; available in PMC: 2021 Jan 1.
Published in final edited form as: Neuroinformatics. 2020 Jan;18(1):59–70. doi: 10.1007/s12021-019-09426-x

Figure 2.

Figure 2

Performances of different imputation techniques, for a varying percentage of missing values based upon the missing completely at random (MCAR) assumption. Imputed values were compared against the gold standard (GS) values. Techniques include random forest (RF), k-nearest neighbors (KNN), low-rank matrix approximation (MA), and mean. The gray zone around each line displays 0.95 confident interval around at each percentage.