Single imputation method

For view 2a, however, LOCF has two severe disadvantages. First, as a single imputation method it makes the very strong and unlikely to be realistic observation that patients could have been expected to continue to have the same general level had they stayed in the trial. The second is that it is a single imputation method and hence does not express the uncertainty inherent in imputation itself. See Section 11.2.8 for a discussion. 

Generally, single imputation can easily be implemented and thus allows the application of the standard complete-data method of analysis. However, the under-... 

MI builds on the advantages of single imputation. It allows the use of complete-data analysis methods for data analysis and also includes the data collector s knowledge. In addition, it incorporates random error because it requires random variation in... 

The problem with any imputation method wherein a single value is substituted for the missing data and then the data set is analyzed as if it were all complete cases is that the standard errors of the model parameters are underestimated because the sampling variability of the imputed values is not taken into account. For this reason... 

FIGURE 9.1 Performance of the conditional multiple imputation and fractional single multiple imputation (LLOQ/ ) methods under the fourth scenario (i.e., assuming 45% interindividual variability and 25% residual variability) for the following parameters (A) AUCo-inf, (B) %AUC extrapolated, and (C) terminal half-life (Lambda Z HL). 

---