Skip to main content

Table 1 Data structure for the Melbourne Collaborative Cohort Study dataset

From: The impact of missing data on analyses of a time-dependent exposure in a longitudinal cohort: a simulation study

Covariate Variable type Grouping/measurement Label Correlation with WC 1
Waist circumference wave 1 Continuous Centimetres WC1 1.00
Waist circumference wave 2 Continuous Centimetres WC2 0.81
Age Continuous Years Age 0.18
Sex Categorical 0 = Males - -0.52
   1 = Females Female -
Education Categorical 0 = None or primary school - -0.18
   1 = Secondary or trade school Education secondary -
   2 = Tertiary education Education tertiary -
Country of birth Categorical 0 = Australia/New Zealand - 0.19
   1 = United Kingdom COB UK -
   2 = Mediterranean COB Mediterranean -
Smoking status Categorical 0 = Never smoked - 0.17
   1 = Former smoker Smoke former -
   2 = Current smoker Smoke current  
Physical activity score Categorical 0 = 0 - -0.13
   1 = (0 to 4) Physical low -
   2 = [4 to 6) Physical moderate -
   3 = 6+ Physical high -
Alcohol consumption Categorical 0 grams (Male & Female) - 0.05
   1-39 grams (Male) / Alcohol low -
   1-19 grams (Female)   
   40-59 grams (Male) / Alcohol moderate -
   20-39 grams (Female)   
   60+ grams (Male) / Alcohol high -
   40+ grams (Female)   
  1. *Correlation with waist circumference at wave 1 was obtained from the observed data of the Melbourne Collaborative Cohort Study participants who attended both waves (i.e. 26,846 participants).
  2. Notwithstanding the limitations of correlations for categorical variables.