from Amazon
Wednesday, September 07, 2011
Does a jump in 2nd half team performance mean something for next year?
RJ has the data here. Specifically, his 23 teams have a 1st half win% of .399. In the 2nd half, they have a win% of .549. Overall, that makes them .474. That fact alone is enough for us to expect them to post a higher win% in the following year. The question on the table though is if .399/.549 will lead to a higher win% than say .474/.474. Unfortunately, RJ doesn’t give us a control group here. We can estimate it quickly by regressing to the mean by adding 69 games of .500 ball. So, .474 in one year would imply .482 in the next year.
How did they actually do? Their gain year to year was .002, to .476. Indeed, it’s a tiny bit worse than expected (though easily within the bounds of random variation).
If we can’t see the effect in the most extreme cases, then chances are, using this as an indicator is not going to be terribly helpful. You are far better off looking at individual players, rather than looking at change in team wins from the first half to the second half.
Here’s the data I used from his chart:
Recent comments
Older comments
Page 1 of 344 pages 1 2 3 > Last »Complete Archive – By Category
Complete Archive – By Date