Improving upon the efficiency of complete case analysis when covariates are MNAR (10.1093/biostatistics/kxu023)
1. Simulation study: correction to Table 1
The third and fourth column headers of Table 1, reporting the results of the simulation study, should have read 
and 
.
2. Application to NHANES: correction of variable definition
The main manuscript stated that 
(average no. drinks per day 
1) was used as covariate in the model of interest in the analysis of data from NHANES. This was incorrect: 
(average no. drinks per day) was used as covariate. For the ACC and MI estimators, the number of drinks minus one was imputed using negative binomial regression. Lastly, it was not stated in the manuscript, but should have been, that BMI was centred at 25 kg/m
.