Table 8 Average classification accuracies of the MVI methods for the categorical datasets
From: Adaptive multiple imputations of missing values using the class center
Dataset | Accuracy (%) | |||||
|---|---|---|---|---|---|---|
Mode | SVM | KNN | RF | CCMVI | AMICC | |
Balance scale | 60.310 | 60.963 | 60.451 | 63.034 | 67.222 | 79.285 |
Breast cancer | 95.285 | 95.282 | 95.951 | 96.026 | 96.321 | 98.713 |
Lymphography | 74.662 | 75.703 | 76.959 | 75.594 | 82.892 | 87.072 |
Promoters | 78.943 | 79.698 | 86.792 | 84.868 | 94.189 | 95.472 |
Spect | 79.371 | 79.251 | 79.026 | 79.401 | 80.389 | 86.941 |
Tic tac toe | 74.342 | 76.929 | 80.965 | 80.403 | 78.854 | 79.708 |
Average | 77.152 (6) | 77.971 (5) | 80.024 (3) | 79.888 (4) | 83.311 (2) | 87.865 (1) |