Pretty please?

This procedure requires us to become comfortable with probabilistic thinking. While a majority of players of a certain type may progress a certain way – say, peak early – there will always be exceptions. Moreover, the comparable players may not always perform in accordance with their true level of ability. They will sometimes appear to exceed it in any given season, and other times fall short, because of the sample size problems that we described earlier.

PECOTA accounts for these sorts of factors by creating not a single forecast point, as other systems do, but rather a range of possible outcomes that the player could expect to achieve at different levels of probability. Instead of telling you that it’s going to rain, we tell you that there’s an 80% chance of rain, because 80% of the time that these atmospheric conditions have emerged on Tuesday, it has rained on Wednesday.

Surely, this approach is more complicated than the standard method of applying an age adjustment based on the ‘average’ course of development of all players throughout history. However, it is also leaps and bounds more representative of reality, and more accurate to boot.

From The Science of Forecasting. That’s a free article, btw.

Of course, I just spent like 5 minutes on these posts when it’s not even important because this topic is about CHONE. And I don’t know if CHONE is an average or not (I think it is, but I could be wrong). I have seen percentile ranges for CHONE before, so maybe it’s like PECOTA.

I suspected Pecota would give you distributions, but I don’t get to see those pages.

I agree with sd – the utility of these systems – really anything that picks one number, a most likely or an average, out of a distribution, is to look at populations. Comparing teams like was done in this article is fine. Becuase some averaging out is bound to happen. Tails cancel out.

The problem I’m addressing is that people look at projection systems and say “Hey, according to XXX, no one will have 40 home runs! No one will have a sub 3.50 ERA! No one will have an OPS above 950.” But players will. Of the 1000 some-odd players who’ll play in 2010, several will exceed expectations by a lot. Which is why that sort of thing can’t be looked at using these projection systems. But if you’re comparing the averages, like sd did here, there is something to be gained. The problem is that when the teams are kind of close (as they are here) you can’t really say much more than that. Luck will play a big role.