1
Missing data on effects and costs were imputed using multiple imputation techniques.
2
For all outcomes, multiple imputation was used to account for missing data.
3
We used multiple imputation with chained equations to estimate missing values.
4
Missing data for plasma cholesterol and vitamin C were imputed using multiple imputation.
5
For missing data, multiple imputation and responder analyses were performed.
6
We used multiple imputation to correct estimates of prevalence and association for loss to follow-up.
7
Results were robust to various sensitivity analyses such as competing risk analysis and multiple imputation.
8
We used multiple imputation to account for missing data.
9
Analyses were done by intention to treat, per protocol, and sensitivity analyses using multiple imputation.
10
Further research is required into multiple imputation methods to address missing data issues in IV estimation.
11
This study is a first step towards defining appropriate use of multiple imputation in longitudinal studies.
12
Prevalence and correlates were estimated using multiple imputation.
13
The base case analysis used an intention to treat approach on the imputed dataset using multiple imputation.
14
We used intention-to-treat analysis, with multiple imputation for missing data, which was concealed to treatment group allocation.
15
We used multiple imputation to impute missing confounder data for 29% of the study participants.
16
We conclude that multiple imputation provides a practicable approach that can handle arbitrary patterns of systematic missingness.
