Skip to main content

Table 5 Estimates of the logistic regression coefficient (φ 1 ) under four analysis methods (n = 100, δ = 1); True value = 0.5

From: Evaluation of a weighting approach for performing sensitivity analysis after multiple imputation

  Number of imputations (m)
  5 10 50 100 500 1000
Full dataset (before deletion) 0.524      
Complete Case Analysis 0.329      
Multiple Imputation under MAR 0.331 0.332 0.331 0.331 0.332 0.332
Sensitivity Analysis under MNAR 0.546 0.601 0.693 0.727 0.781 0.797
  1. Note: The empirical Monte Carlo standard errors were all around 0.008 for MI for sensitivity analysis