Skip to main content

Table 8 Simulation results of random effects expectation–maximization (REEM) tree algorithm for diastolic blood pressure (DBP)

From: A wide range of missing imputation approaches in longitudinal data: a simulation study and real data analysis

Imputation method

MSE

RMSE

MAD

Deviance

Interpolation LOCF

0.8527485

0.9234451

0.7243289

41396.3

Interpolation global

0.8555876

0.9249804

0.716464

42286.06

Interpolation local

0.8602081

0.9274721

0.6975486

43665.6

Interpolation bisector

0.8555478

0.9249548

0.7164404

42292.76

copyMean.LOCF

0.8528052

0.9234774

0.7245612

41397.91

copyMean.global

0.855585

0.9249841

0.7165564

42285.6

copyMean.local

0.8601975

0.9274707

0.6977025

43666.37

copyMean.bisector

0.8559014

0.925148

0.7141584

42402.8

LOCF

0.8537565

0.9239873

0.7304617

41693.62

NOCB

0.8537621

0.9239997

0.7302594

41683.84

Traj mean

0.8504812

0.9222132

0.6835874

40742.72

Traj median

0.8507346

0.9223542

0.687355

40833.42

Traj hot deck

0.8538656

0.9240471

0.7318596

41769.81

Cross mean

0.8693141

0.9323711

0.73382

41858.75

Cross median

0.8693081

0.9323664

0.7338405

41860.46

Cross hot deck

0.8799369

0.9380265

0.7386661

44022.77

FCS-LMM

0.9835786

0.9917558

0.7716194

416116.5

FCS-LMM-het

0.9835786

0.9917558

0.7716194

416116.5

FCS-GLMM

0.9833765

0.9916557

0.7890735

399160

FCS-LMM-LN

0.9833792

0.9916543

0.7874033

399770.8

FCS-LMM-LN-het

0.9833914

0.9916603

0.7856904

401880.2

JointAI

0.9833758

0.9916535

0.7875987

399447.3

hmi

0.9833762

0.9916535

0.7876294

399314.6

JM-SMC

0.9833776

0.991653

0.7876414

399511.8

JM-SMC-het

0.9833189

0.9916236

0.7871983

399572.9

JM-MLMM

0.9833767

0.9916536

0.7875398

399486.1

JM-FJ

0.9833752

0.9916533

0.787628

399484.6