Quote:
Originally Posted by BPS
I have been talking about statistical issues involved in model selection when the data you have is limited and given to you by someone else.
You want to talk about discovering the model within software when you have the ability to generate as much data as you'd like.
These are very different things. Only the first is relevant to thinking about the existence of clutch hitting in the real world.
|
Then, yes, by definition, it's always possible to code something that is too small to find in a small sample set.