Figures & data
Table 1 An example of a situation when data are MAR rather than MCAR
Table 2 Proposed methods for dealing with missing data in the analytic phase
Figure 1 Distribution of BMI values by outcome in full dataset (A) and in a dataset with 35% missing values (B) for BMI handled by creating a missing BMI category.
![Figure 1 Distribution of BMI values by outcome in full dataset (A) and in a dataset with 35% missing values (B) for BMI handled by creating a missing BMI category.](/cms/asset/0301f62e-b075-455a-abf5-10004aff37e0/dcle_a_129785_f0001_c.jpg)
Figure 2 Normal distribution of observed BMI in a full dataset of 10,000 observations.
![Figure 2 Normal distribution of observed BMI in a full dataset of 10,000 observations.](/cms/asset/30bcf3a7-97b4-465f-9b1f-0a46c148b32a/dcle_a_129785_f0002_c.jpg)
Figure 3 Distribution of BMI in a dataset of 10,000 observations, where 35% of BMI values are missing and replaced by the observed mean BMI value.
![Figure 3 Distribution of BMI in a dataset of 10,000 observations, where 35% of BMI values are missing and replaced by the observed mean BMI value.](/cms/asset/8dbb2e1e-9c90-459f-82a2-687b6ea93fc5/dcle_a_129785_f0003_c.jpg)
Figure 4 Selection of variables in order to create multiple imputed datasets when looking into the association between body mass index and transfusion risk.
![Figure 4 Selection of variables in order to create multiple imputed datasets when looking into the association between body mass index and transfusion risk.](/cms/asset/1891d866-80bf-4aed-b011-b45d1c3e7f51/dcle_a_129785_f0004_c.jpg)
Table 3 An example of the imputed missing BMI values generated with five imputed datasets
Table 4 Association between BMI and risk of blood transfusion adjusted for age and gender