-
How to deal with this categorical predictor in linear regression?
updated 4 years ago
2 Members
·
2
Posts
-
Suppose we are building a linear regression model. We have a categorical variable with 4 levels. We used dummy coding and run stepwise selection. Finally, the results show that only one level of this categorical variable is significant and the remaining levels are insignificant.
So should we include this predictor in our model or not?
-
In this case, we use F-test to check on this categorical predictor. Test the reduced model against the full model, if it is insignificant, then we just drop it.
If it is overall significant, but few levels are NOT significant. We can then regroup it by combining the insignificant levels, which will make more sense for this variable.
Log in to reply.