Table 1 The optimal hyperparameter configuration of machine learning imputation techniques (under the MAR (the ratio of missing proportion 1:2) mechanism scenario with a missing proportion of 5%)

LR

–

–

–

–

RF

randomForest

mtry: number of randomly selected predictors

mtry = {1:8}

mtry = 4

NN

nnet

size: numbers of hidden units, decay: weight decay

size = {1:24}, decay = {0, 0.1, 0.01, 5e-4}

size = 4, decay = 0.1

SVM

Kernlab

sigma: Sigma^*, C: cost

Kernel = Radial Basis Function Kernel, C = {0.25, 0.50, 1, 2, 4, 8, 16, 32}

Kernel = Radial Basis Function Kernel, C = 0.25

EL

kernlab, caret, caretEnsemble

sigma: Sigma^*, C: cost

Kernel = Radial Basis Function Kernel, C = {0.25, 0.50, 1, 2, 4, 8, 16, 32}

Kernel = Radial Basis Function Kernel, C = 0.25