Quote:
Originally Posted by x McLovin x
First off, I was speaking in generalities to prove a point, that while it wasn't the case with Bryant, that it could very well happen with someone else.
|
I forgot to address this. It
could happen and likely does. One of the first things you learn when you study quantitative analysis is if you're data set shows 100% correlation there's something wrong with your data. That means you have exact multicollinearity and that's bad. That said, I would posit that if you put the data for all MLB batters into the computer you will find a
very high correlation between HR rate regardless of how you measure it and AEV. There will be exceptions, there always are, but I would predict not many. And if you do find a batter with an exceptionally low AEV but high HR rate, and this has been consistent through time, anyone with experience in quantitative research knows there's something else going on, another variable (called confounding variables) that wasn't accounted for but had it been would have predicted the HR rate. I would also safely predict this kind of outlier being extremely rare. The real life example of Kris Bryant showed that HR rate (plus doubles rate) predicted AEV. Given that, knowing the former meant I didn't need to know the latter.
But what do I know, I'm an old ignorant codger.