I would like to test is a given variable is associated with both the dependent and the independent variables (and therefore a potential confounder) in a repeated-measures design.
My model has a continuous dependent variable and two independent variables: a within-subject factor with 6 levels and a between-subject factor with 2 levels. I also have a continuous independent variable that is statistically associated with my between-subject factor (tested using a 2 sample t-test).
How should I test the association between this continuous variable and the dependent variable?
(1) adding this variable to my original model and check the effect of this extra variable?
or
(2) fitting a new model with only my within-subject factor and this extra variable (i.e. without the between-subject factor)?
I would probably go for method 1. This is Greenland's change in coefficient method. If the parameter(s) of interest change by (say) 10% or more after adding the potential confounding variable, then it is considered to be a confounder.
Hi,
Counfounding adjustment by regression allows you to directly check for the effect of the potential confounder on the outcome, and indirectly check for the association between it and the exposure/intervention.
The potential confounder coefficient can be statistically significant or not. If not it is not relevant; if yes there are two options:
1. The coefficient of the main exposure is affected (as Esterman says for at least 10%, relative), and there is a confounding effect.
2. The coefficient of the main exposure is not affected (
- Badges
- Science topic
- Similar topics
- Statistics
- Survey