I have built a Lasso regression model for dataset A. I want to test whether this model works well on dataset B, which has a slightly different scale than dataset A.
I am unsure how I would apply standardisation in dataset B.
- Should I use the standardisation parameters that I used on dataset A?
- Or can I standardise the dataset B predictors based on the dataset B itself?
Since the scale of dataset B is different to A, I was leaning towards the second option. However, I am not sure if there would be any issues with this.