Since 0.500 must be the true-talent average for MLB as a whole, that leaves SQRT(11.9^2 – 6.4^2) = 10.1 wins per team per year to be explained by other factors.

I estimate (long calculation) that salary differences account for another 6.4* wins/team/year. That still leaves 7.8 wins/team/year to be explained.

At the team level, the breakdown appears to be: 28% luck, 28% salary, 43% something else.

]]>I’ve always wondered how well projections worked for the 1969 season. How would those projections have turned out? All the distributions couldn’t have factored in the lowering of the mound. I’m guessing that not having that data would have skewed everything. So projections are always limited to the data you have before hand and sometimes your prior sampling data is not going to be able to predict the new population probability distribution going forward. Especially with rule changes and things like new ballparks.

]]>The chances of me getting that exact hand are 1 in three million! I must not have it!

]]>However, given 100 players with true talent estimates, we would actually expect a few guys to put up performances way out in the tails (2+ SDs from the mean) — even if we nailed the true talent estimates.

The whole probability distribution concept and it’s associated considerations (e.g. sample size) is just fundamental to understanding statistical analysis. Great article, Steve!

]]>