Quote:
Originally Posted by BPS
But if M1 and M2 generate very similar data, the data can't speak about which model generated it.
|
This is not correct with regard to software models. With software models as we know them, it's always possible to determine which model created which data set as long as you take enough data.
If you force yourself to study only a playoff series worth of data, though, then of course you will not be able to see anything in the two data sets. This is a trivial case, though, since you can say that regardless of whether we're talking about clutch hitting or power.
Quote:
|
I've said this a couple of times. But it seems you are interested in other things. That's okay. People are interested in different things.
|
I don't understand your statement. You said it's easy to code "clutch" in the game in such a way as to be undiscoverable in the data. I don't think that's true unless you artificially constrain yourself to small data sets.
If you change your statement to "it's possible to code a game with clutch rating and then give you such a small sample set that you can't find it," I'll agree, but say: so what? That's like saying 1+1 = 2 to me.
Regardless, I don't think we're doing much of value here, so ...
