what is the difference between these two methods ?
method 1
method 2
Do you think the results of the two methods are the same?
1 Like
Hi @BerkayAkar
Strictly speaking they are not the same.
The first method is doing a feature selection based internally on a cross validation.
The second method is doing a feature selection based on a unique internal training-test data partion at every loop iteration.
The first one should be more accurate on the results than the second one although computationally much more expensive.
If you have a lot of data on which to base your variable selection, I would recommend the second method since statistically both should tend to similar results when dealing with enough data, whilst less computationally expensive.
Alternatively, if you have little amount of data, I would recommend the first method since more accurate in the variable selection results when dealing with little data, although more computationally expensive.
Hope this helps.
Best,
Ael
2 Likes
thanks for giving advice sir
1 Like
!This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.