Table 1.
Mean errors between observed and imputed BMI values, one missing value per individual
| Cases | Methoda | Obs. | Mean | Std.Dev | Min | Max |
|---|---|---|---|---|---|---|
| Allb | Simple ×1 | 10000 | 1.113 | 1.353 | 0.000 | 26.900 |
| mibmi ×100 | 10000 | 1.120 | 1.351 | 0.000 | 26.888 | |
| Twofold ×100 | 10000 | 0.949 | 1.026 | 0.000 | 15.481 | |
| Interpolation | Simple ×1 | 6132 | 0.801 | 0.819 | 0.000 | 11.651 |
| mibmi ×100 | 6132 | 0.808 | 0.819 | 0.001 | 11.429 | |
| Twofold ×100 | 6132 | 0.804 | 0.810 | 0.000 | 11.180 | |
| Extrapolation | Simple ×1 | 3868 | 1.606 | 1.808 | 0.000 | 26.900 |
| mibmi ×100 | 3868 | 1.614 | 1.805 | 0.000 | 26.888 | |
| Twofold ×100 | 3868 | 1.179 | 1.260 | 0.001 | 15.481 |
aSimple refers to a single imputation that ignores variability in the observations (option xsimp); mibmi refers to the default multiple imputation approach with the command and 100 imputations; twofold refers to the twofold algorithm described in the paper and 100 imputations
bAll refers to both interpolations (between observations imputations) and extrapolations (not between observations imputations)