Quote:
Originally Posted by AltonKelsey
"All it does is try to tell you out of the population of horses that breakthrough whether they do better as favorites or not."
Really, that's not what I see. Maybe you're looking at a different study.
I think we might have a pearls before swine situation here.
The study clearly shows breakthroughs are a strong net negative.
Not sure why all the hole poking. If you have a better database , fine, but as cj says, unless this one is totally screwed, the conclusion is clear.
|
I explained earlier, the way this study is set up, the hypothesis being tested is: Among all horses breaking through the gate, how do favorites compare to the population as a whole? I don't think that's what the author is trying to ask. I think what he's trying to ask is, among all horses how do breakthroughs perform compared to the whole population? Or maybe he's trying to ask, among all favorites, how do breakthroughs perform compared to the population of all favorites? In other words, are such favorites vulnerable? For that he would have to do a different study.
This is elementary stats. If you want the right answer you must first ask the right question. if not, your not going to answer the question you want, no matter how correctly the study is done.