Nice work, Jon. I have done this as well, but haven't gotten in publishing shape. I also used data from the last 20 years.

A typical first baseman will lose 1.3 more games in his age 32 season than his age 28 season. Third base is more resilient as only 0.3 games lost in that transition. This retention has a lot to do with the fact that players with the ability to stick at third base will stay there while those who lose range or skill will be shifted to first base.

I didn't RTFA, but it seems to me this comparison is useless. You need to just look at the same players. If a bunch of slugs move over to 1B, it doesn't necessarily mean the guys who were always there are getting worse. They probably are, but it seems these numbers are corrupted by players who we know have lost the skills to play some other position, and are still learning the second position.

All the same, the study looks awesome to me. Really fascinating.

I wouldn't say it is useless. Knowing what you know (that diverse sub-populations exist), you can bend the lines to fit. With guys shifting out of 3B, the peak is probably slightly higher and extends further if the player is a true third baseman. If not, performance will sink more quickly.

As with all general trend lines based on 3 or 4 years of data . . . the lines should not be used as something definite. I would say that Chris' study looks far more comprehensive and it will be interesting to see how his match's up with this one and Tango's SS. The similarity between Tango's and this one for SS is pretty interesting due to Tango's looking more at year to year, where this one is just plopping things down into a population.

Don't have time to read the article now (looks interesting) but based on the excerpt and the quick glance, I'm agreeing with #2. There are two processes going on -- aging and attrition (be it switching positions, moving to the bench, or being out of baseball). Do 3B age well? This would be the first time anyone's suggested they age better than other positions. Or is it that more athletic 3B age well and the other guys have attritted (is that a word?) by age 30? There may also be some small effect from slugging SS shifting to 3B in their 30s.

And of course a lot of the attrition will be due to poor hitting. There must be a lot of this at 2B, especially, and SS. There are always young, slick fielding, no-hitting guys to play 2B and SS ... so when the current one hits 30, why keep him around? The ones who stick past 30 (as starters) are mostly the ones who can hit. In short, the average 32 y.o. 2B is probably a good-hitting average-or-worse fielding 2B ... but that same player at 26 was probably a good-hitting average-or-worse fielding 2B. But you'll find a lot more 26 y.o. good fielding, poor hitting 2B (getting playing time) than you will 32 y.o. ones. (Or so I'd guess.)

Put another way, Tony Pena Jr is a fine fielder and he made 26 y.o. SS look pretty good in the field last year. He will not see age 30 in a major-league uniform and that will have nothing to do with any defensive decline.

Which isn't to question the debilitating impact of age -- that's obvious. It's the magnitude that we need to get as specific about as we can.

Do 3B age well? This would be the first time anyone's suggested they age better than other positions.

Disagree. When I saw that graph my immediate thought was that it confirmed my hunch on exactly that point.

I would say that there the general opinion on the position is that it, more than almost any other, demands years of in-game learning to master. That is needs technique more than it does athleticism. If a 24-year old is a poor defensive shortstop, you talk about moving him to second. If a 24-year old is a poor defensive third baseman, the frequent comment is that he will be able to learn and improve as he ages.

I can think of more 3Bs whose defensive reputation grew as they turned 30 (Caminiti, Boggs, Fryman, Brosius, Lowell...) than I can at any of the more athletic positions.

Apologies for very sloppy editing above ("that there the," "that is needs")

Here's the aging curve I get for third basemen. I think that these curves look way too drastic at the ends - not that mine doesn't at the far right either.

Nice comments, guys. I noticed some traffic coming in.

Chris - Thanks
Chicken - Yeah, your quoting me basically. I completely agree with what you write, except the useless part. That, as Lou said, is a bit hyperbole. You have to take these graphs for what they are and what I could acquire. The data sets I have and the restrictions I placed on them limited what I could do. If I did what you suggest, and I did at first, you wind up with too few data points that are skewed by peculiarities. Basically, it becomes a bunch of player specific growths and I was not interested in that. Again, this is to be taken as a general stab at things.
Fish - Thanks
Walt - Yep on many accounts. Except, it has been mentioned often that 3B tend to age well because range is less of a requirement for them. Couple that with SS with strong arms getting placed there. You get a different demographic than 1B.
Colin - Your graph and mine are incredibly similar. I can see you didn't restrict the data, but realize that you graph is close to being a derivative of my own. I think the way you use yours is artificially bumping up the end with guys who were kept there. My data set ignored solitary guys on the age spectrum. I think this is a more apt way to determine the typical growth.

Anyway, thanks for the interest. It is great to read some feedback. I very much look forward to Chris blowing this study out of the water. :)