In this regression, we will again explore the links between childhood intelligence and body mass index (BMI) at age 42, but this time we will categorise participants’ BMI score into three groups: ‘normal/healthy’, ‘overweight’ and ‘obese’. We are going to treat this variable as being nominal and so we will use a method called multinomial logistic regression that is appropriate for use with outcome variables with multiple categories.
In the next section, we will show you how to create the variable for use in the analysis.
The Learning Hub is a resource for students and educators
tel | +44 (0)20 7331 5102 |
---|---|
closer@ucl.ac.uk |
Sign up for our email newsletters to get the latest from CLOSER
Sign up