Farm system success

Flip Flop Flyball has had a number of good infographics (and humour items) in the past, but their recent "Wins and loses throughout each team's system" chart is particularly interesting.  One thing that caught my eye is that no team in the Houston Astros system managed to break the .500 mark in 2011.

This raises a question in my mind. Can the current performance of minor league afflitates be used to predict MLB team performance at some future date?  (Economists would call this a leading indicator.)  All of the research on minor league performance that I'm aware of is in service of forecasting individual player performance. For good review of that work, see "The Projection Rundown" at Fangraphs.

But I'm wondering if the fluid nature of the minor leagues will yield any sort of meaningful result at the team level.  Not only are players constantly moving up and down between the levels, it also seems to me that they are every bit as likely (if not more so) to move mid-season from one organization's farm system to another (resource: Baseball America's listing of minor league players).  And the farm teams themselves are prone to shifting from one organization to another, and moving up and down the levels.  As one example, the Vancouver Canadians of the single-A Northwest League were affiliates of the Oakland A's for 11 seasons, but in 2011 came under to Toronto Blue Jays umbrella (they finished with a 0.513 record, second in their division).

Which then leads me back to the infographic: other than 2011 results, does it tell us anything?

-30-

World Series prediction: the Bill James method

Bill James developed a method for predicting playoff series winners, last updated in the 1984 edition of Baseball Abstract in an essay titled "The World Series Prediction System, Revisited".  At that point, it had a pretty good track record -- 73% success in predicting the winner of all the postseason series in the 20th century.

Mike Lynch over at seamheads.com used the method (without any adjustments, updates, or other tweaks) to predict the 2010 World Series -- which correctly identified the Giants.

This year, Lynch has again used the tool and tabulated the Rangers and the Cardinals according to the Bill James method. 

The result:  the Rangers come out as solid favorites.

(A couple of other older references to previous use of method are here and here. Other than that, I haven't found anything on the web that uses or updates the method.)

-30-

World Series prediction

The 2011 World Series starts in a couple of days, and it's time for the pundits to come out and make their predictions.  Over on coolstandings.com they've posted their prediction for the World Series.  Here's a screenshot of their "smart" prediction:

(The "dumb" prediction is 50/50 for either team, so there's no point talking about that. And I've posted a screenshot, since their predictions are live and will change upon the outcome of the first game of the World Series. An example of the Monty Hall problem, in real life.)

To summarize:  Texas shows as having a 68.2% probability of winning the World Series.

I'm not sure of the details of their methodology, but we can use each team's regular season win/loss record to employ the "log5" approach to come up with our own prediction.  So I did that, and my first prediction is for a Texas victory (58% probability) -- and if pressed to predict the series length, it would be Texas in 6 games (17% of the outcomes are Texas 4-2).  Both probabilities are substantially lower than the coolstandings prediction.

But we can be a bit more sophisticated in our approach, using an adjusted win/loss percentage that employs a Bayesian adjustment to each team's final result.  (This is the same method I used back in May for the early season results -- after 162 games the impact of the prior is much reduced.) This changes Texas' winning percentage to 0.571, and St. Louis to 0.543.  (Google doc spreadsheet here.)  Using the log5 formula, this gives the Rangers a 0.538 edge over the Cardinals.

Working through the 7 game series, Texas' probability of winning the World Series is 56%.

And we can be still more clever, by considering the road/home splits of each team.

Team      W-L     %   posterior
-------- -----  ----  ---------
Texas    96-66  .593   .571
- home   52-29  .642   .591
- road   44-37  .543   .527


St Louis 90-72  .556   .543
- home   45-36  .556   .535
- road   45-36  .556   .535


The home-road splits improve things for the Cardinals, since they had a better home record than Texas' road record and thus become more likely to win a home game. As well, the Cardinals have home field advantage (but only on game 7 -- the Rangers have home field advantage in a 5-game series. But I digress.)  After using the home-road splits, Texas still remains the favorite, but the probability is down to 54%.

While my approaches still give Texas the biggest likelihood of victory, my estimates are less emphatic than the probabilities over at coolstandings.  Based on the characterizations used at coolstandings, my methods lie somewhere between "dumb" and "smart".  "Average intelligence", perhaps.

Tow Mater says "Rangers in 6. But I had the Phillies and the Brewers beating the Cardinals, too".

-30-

Gelman on baseball

Andrew Gelman has published a few blog articles lately that hit on baseball.

First up, "Bill James and the base-rate fallacy", where he points out a flaw in James' reasoning that arises from the "availability heuristic".

Second, at The Statistics Forum, a comparison of predicting future performance at a significant transition point in "Minor-league Stats Predict Major League Performance, Sarah Palin, and Some Differences Between Baseball and Politics".

I don't have anything to add, other than to say it's encouraging to see one of the best statistical thinkers in the academy using baseball as a point of reference.

-30-

Graphing run expectancy

Baseball Prospectus provided the world with the 2010 situational run expectancies, and Joshua Maciel has provided a graphic display. The graph was first posted to and then evolved as a result of feedback from readers at Tango's blog -- a fascinating process in and of itself. The graph is still a bit busy to my mind (but it's certainly not a Tufte-ian duck...), but it's a fine piece of work displaying what is arguably one of the most important pieces of baseball data.

And remember, it was George Lindsey who first published these data, back in 1963.

[Right: Joshua's run expectancy chart. Click to see it full-size, and visit his blog for all the details.]

-30-

World Series predictions

The 2010 World Series starts this evening, and many pundits are making their predictions on who will win (a sample: The Baseball Analysts, New York Times, and Sports Illustrated.

But perhaps the best way to think about evaluating the pundits is contained in this article "Slick talkers and bad forecasters" by Dan Gardner. Gardner's article is about economic forecasting, but the point is relevant -- when it comes to predicting the outcome, a nuanced understanding of all of the influencing factors produces the best forecast. Or as Gardner puts it, "experts who gathered information from many sources, who were comfortable with complexity and uncertainty, and were more prepared to admit mistakes and adjust conclusions accordingly -- these were the experts worth listening to."