Skip to main content

Table 1 Results of the simulations on linear regressions, MAR(Y)

From: Auxiliary variables in multiple imputation in regression with missing X: a warning against including too many in small sample research

Percent missing   Auxiliary variable correlation n = 50 n = 100 n = 200
    Bias SE Std. Bias RMSE Bias SE Std. Bias RMSE Bias SE Std. Bias RMSE
20 CC - −0.13 0.33 −0.43 0.20 −0.13 0.22 −0.60 0.17 −0.13 0.15 −0.85 0.15
  MI+0 - −0.05 0.32 −0.11 0.16 −0.03 0.22 −0.10 0.11 −0.02 0.15 −0.09 0.08
  MI+10 0.1 −0.08 0.33 −0.21 0.17 −0.04 0.22 −0.17 0.10 −0.02 0.15 −0.10 0.07
  MI+20 0.1 −0.16 0.35 −0.43 0.21 −0.06 0.23 −0.26 0.12 −0.03 0.15 −0.16 0.07
  MI+40 0.1 −0.28 0.35 −0.77 0.32 −0.17 0.24 −0.66 0.19 −0.05 0.16 −0.32 0.08
  MI+80 0.1 −0.25 0.35 −0.70 0.31 −0.30 0.27 −1.13 0.33 −0.16 0.17 −0.94 0.17
  MI+10 0.5 −0.06 0.45 −0.10 0.23 −0.03 0.30 −0.06 0.15 0 0.21 0 0.11
  MI+20 0.5 −0.13 0.46 −0.25 0.26 −0.05 0.30 −0.14 0.17 −0.02 0.21 −0.07 0.10
  MI+40 0.5 −0.20 0.44 −0.46 0.33 −0.12 0.33 −0.37 0.19 −0.04 0.21 −0.16 0.11
  MI+80 0.5 −0.21 0.44 −0.45 0.34 −0.43 0.33 −1.37 0.43 −0.12 0.23 −0.53 0.16
50 CC - −0.14 0.57 −0.32 0.44 −0.25 0.35 −0.72 0.34 −0.23 0.25 −0.96 0.27
  MI+0 - −0.13 0.44 −0.20 0.33 −0.08 0.29 −0.18 0.23 −0.06 0.21 −0.20 0.17
  MI+10 0.1 −0.27 0.47 −0.52 0.38 −0.13 0.30 −0.36 0.22 −0.07 0.20 −0.29 0.15
  MI+20 0.1 −0.59 0.48 −1.30 0.60 −0.23 0.33 −0.68 0.28 −0.10 0.21 −0.43 0.15
  MI+40 0.1 −0.52 0.42 −1.28 0.59 −0.57 0.33 −1.82 0.57 −0.21 0.23 −0.94 0.23
  MI+80 0.1 −0.50 0.42 −1.21 0.58 −0.54 0.29 −1.95 0.59 −0.56 0.23 −2.54 0.56
  MI+10 0.5 −0.23 0.63 −0.33 0.42 −0.09 0.41 −0.15 0.32 −0.03 0.28 −0.06 0.17
  MI+20 0.5 −0.50 0.59 −0.90 0.52 −0.18 0.44 −0.39 0.31 −0.06 0.28 −0.16 0.21
  MI+40 0.5 −0.45 0.50 −0.94 0.61 −0.51 0.41 −1.31 0.51 −0.18 0.31 −0.57 0.25
  MI+80 0.5 −0.43 0.51 −0.89 0.61 −0.43 0.35 −1.28 0.57 −0.51 0.29 −1.85 0.51