We excluded those with missing data for the primary exposure (ethnicity) and outcome of interest (SARS-CoV-2 infection) from all analyses.
Multiple imputation by chained equations was used to impute missing data in these logistic regression models. The imputation models included all variables used in the final analyses bar those being imputed, including the outcome measure.
Risk factors associated with SARS-CoV-2 infection in a multiethnic cohort of United Kingdom healthcare workers (UK-REACH): A cross-sectional analysis
PLoS Med. 2022 May 26;19(5):e1004015. doi: 10.1371/journal.pmed.1004015. eCollection 2022 May.