from Amazon
Thursday, July 16, 2009
A glaring example of how NOT to use a regression analysis
A few disclaimers and qualifiers: Dan is a good guy and a good researcher. I am by no means an expert in regression analysis. I don’t even play one on TV. Dan fully admits that there are problems with his methodology.
I am not sure why he even published this though. The results are clearly bad - partially at least because of the methodology (the variables he used in the regression).
I don’t think you need to do a regression analysis for something as simple and obvious as GDP rate. And if you do, I think it is pretty obvious that the only significant variables to use are handedness, speed, percentage of GB per PA, and how hard you hit the ball which you can proxy with any number of variables I would think.
The only other possible variables I can think of would be pull ratio independent of handedness (for example, Ichiro may hit into more DP because he may hit more balls to the SS side than the typical speedy left-hander), an ability to deliberately hit the ball to some beneficial location in a DP situation, if that even exists, and whether the runners on first base tend to me in motion more than is typical when you are at bat.
Recent comments
Older comments
Page 1 of 343 pages 1 2 3 > Last »Complete Archive – By Category
Complete Archive – By Date