Yes I understand this (I actually do a lot of machine learning). The normal way you do this is you at least split your data in two before analysis, use cross validation on half to develop your model, and then test the model on the other half of the data.
When doing research the easiest person to fool is yourself.
Ann: Positive Results from Australian Adult Clinical Studies, page-20
Currently unlisted. Proposed listing date: 4 SEPTEMBER 2024 #
-
- There are more pages in this discussion • 52 more messages in this thread...
You’re viewing a single post only. To view the entire thread just sign in or Join Now (FREE)