Monday, March 29, 2010

BASEBALL "STATISTICS"

I realize this is a long and rather heady post - especially if you're not much into math.  I posted this recently to Tom Tango's blog as a comment to an article about statistical significance.  I dragged it over here for safe keeping.

*   *   *   *   *

I apologize if I’m butting in the middle of a conversation, but there’s been an issue that’s been bugging me for years and it seems appropriate here.

When I was in college (some 30 years ago), one of my statistics professors scolded me (as best I can remember), “You baseball guys have it all wrong.  You treat a set of baseball statistics as if they are a random sample and run all of your significance tests.  Baseball statistics are not a random sample of anything - they are a full and complete set of data.  To analyze them using statistical techniques is a misuse of the science.” Being as stubborn as I was back then, I disagreed with him.  But as the years have past, I never forgot what he told me and now in my middle-aged years have come to believe that what he said has some merit.

Take clutch hitting.  Suppose Larry bats 17 for 50 (.340) in clutch situations and 100 for 400 (.250) in non-clutch situations.  A standard statistical test will tell you that the difference between these two proportions is not significant at either a 95% or 90% confidence level, therefore you can not conclude with a high degree of certainty that Larry is a better hitter in the clutch.

But the fact is that Larry WAS a better hitter in clutch situations - a MUCH better hitter.  Those 17 hits he got probably won his team a few games that they otherwise would not have won.  That is very significant.  To apply a statistical test to this data and conclude that we can not prove that Larry is a good clutch hitter is to say that there are other at-bats that Larry had that we don’t know about and if you measured those, the difference in his average might not be as great.  This simply isn’t true.

Another analogy would be the U.S. Senate voting on a bill.  If 51 Senators vote in favor of the bill and 49 vote against, even though a statistical test would tell you that there is no difference between to proportion of Senators who are in favor of or oppose the bill, this is regardless a very significant outcome because there are no other Senators to ask.  You can say with 100% certainty that more Senators are in favor of the bill than not.  Just like you can say with 100% certainty that Larry was a better clutch hitter than not.

When we analyze random samples of data, we do so to predict that which we can not measure, or is impractical to measure, or is too expensive to measure.  If we have a machine that fills boxes with breakfast cereal, we don’t tear open every box at the end of the assembly line to be sure they are filled properly.  We only test a sample and then assume that the others have similar characteristics.  But in baseball we do measure everything.  EVERYTHING.  There is no data that is unknown.  When we apply statistical techniques to this type of data, we area only analyzing events that will never occur.  Perhaps a fools errand.

*   *   *   *   *
A couple of posters jumped all over this saying things like the set of at bats a player gets is a random sample of all of the at bats he could have gotten from an infinite set of possible at bats.  Or this:

If the 50 clutch AB’s (in which the hitter got 17 hits) ARE the complete data set, then there can’t be any other elements in that set, and therefore any clutch AB that arises later must be from another set, right?  In which case the prior data has no relevance, right?  In which case, what value does the designation of this hitter as a clutch hitter have?  None. --Greg R
I think these guys are wrong.  I also think that their opposition to my point of view is in part their trying to justify what they've spent much of their lives doing.

Mathematical statistics are central to my day-job career of market research.  In it, I've seen a lot of abuse of statistical techniques.  Anyone with a computer can run a regression analysis, but as with many tools, in the wrong hands they can do more harm than good.  Chainsaws come to mind.

If there are any math gurus reading (John R), I'd love to get your take.

UPDATE:  There's a vigorous discussion going on on this topic in the comments to the original post,  including a mea culpa by me for calling analysts who I respect "wrong".  I should have simply said that I disagree with them.  My bad.

UPDATED: JEFF SUPPAN VIGIL

Monday, March 22, 2010

OVERTIME

Why doesn't the NFL just modify its overtime rules to say that the last team to score in regulation must kick off in overtime?  I've told a million people this idea and no one can see a downside.  This change would not, on average, add any extra playing time to games; which they seem concerned about because of injuries.  In fact, it would add strategy to regulation and perhaps reduce the number of overtime games as teams would be more apt to play for a win than a tie late in a game, knowing they would have to kick off in overtime if they tied.  I'm shocked that no one in the NFL has thought of this.

Sunday, March 21, 2010

JEFF SUPPAN VIGIL


It's been a while since I've lit the In-Between Hops vigil.  Ned Yost was the last time I believe.  But now seems like an appropriate time to light it again.  With the other options available to them, I do not see how the Brewers can justify keeping Jeff Suppan on the team.

It's sad in a way because his baseball eulogy will read well.  He is, by every indication, an outstanding individual who gives back to his community.  Perhaps there is a future for him on a coaching staff, in a broadcast booth, or front office.  Or perhaps too, the $60 million he earned as a player - 70% of which came from the Brewers, the team to which he gave about 10% of his production - will allow him to carry on comfortably from here. But his career as a baseball player is in its waning days.

Friday, March 19, 2010

BREWERS WEEKLY READER

It's not my thing to rip on other sports writers. Everyone has their own style and skill level.  Lord only knows how many typos and grammatical gaffes I make myself.  But Anthony Witrado's column yesterday about Mat Gamel was so poorly written and riddled with factual errors that it should have never been published in a major American newspaper.

"It seems like if isn't him screwing himself like he did in his first call-up or first big league camp, then it's a player emerging in front of him or injuries putting him on the shelf."
I'm sorry, but that's bush.  A lot of sixth graders could have written something better than that.  And that's just a snippet.  The whole article is as bad.

THE MIGHTY HAS FALLEN

Thoughts go out this morning to Vin Scully who is recovering in a Phoenix hospital after falling last night in his home.  Scully has hinted that this may be his final season broadcasting Dodgers' games.  There is no better reason than that to buy a subscription to MLB.TV, for the chance to hear his melodic and often poetic description of a baseball game for perhaps the last time.  There has never been a better baseball announcer than Scully and it's hard to imagine there ever will be again.  Be well, Vin.

Wednesday, March 17, 2010

SUNK COST

Wikipedia says the following about sunk costs:

"Sunk costs are past costs that have already been incurred and cannot be recovered.

"Traditional economics proposes that an economic actor not let sunk costs influence one's decisions, because doing so would not be rationally assessing a decision exclusively on its own merits.

"Evidence from Behavioral economics suggests this theory fails to predict real-world behavior. Sunk costs greatly affect actors' decisions, because humans are inherently loss-averse and thus normally act irrationally when making economic decisions."
This brings me to Jeff Suppan.

The money that the Milwaukee Brewers owe Jeff Suppan is a sunk cost.  They have no way to prevent paying it.  Yet there are all kinds of people in Internet Nation who think that the Brewers must keep Jeff Suppan because of his contract.  These people are thinking irrationally.

There is not a single shred of evidence to suggest that Jeff Suppan is going to be an asset to the Brewers this season.  In Bill James' Gold Mine he says, "The cinematic equivelent of the last five years of Jeff Suppan's career would be the boxer who's felled by the slo-mo knockout punch."

Year Wins ERA AVG OBP SLG
2005 16 3.57 275 335 428
2006 12 4.12 277 343 440
2007 12 4.62 298 356 445
2008 10 4.96 298 361 483
2009 7 5.29 309 387 512

This spring Suppan has given up 12 hits in 9 innings pitched, including 5 home runs, and sports a 7.00 ERA.

If the Brewers are thinking rationally, they will cut Jeff Suppan.  If they think they must keep him simply because of his contract, they could be - well... sunk.

Monday, March 15, 2010

TORRI HUNTER AND THE U.S. CENSUS

Last week, in trying to belabor the point that Major League baseball is not doing enough for African-American players, Torri Hunter made some very ignorant comments about Latin American players (which he has since recanted - sort of.)

"People see dark faces out there, and the perception is that they're African American. They're not us. They're impostors.  Even people I know come up and say, 'Hey, what color is Vladimir Guerrero? Is he a black player?' I say, 'Come on, he's Dominican. He's not black.'

"As African-American players, we have a theory that baseball can go get an imitator and pass them off as us. It's like they had to get some kind of dark faces, so they go to the Dominican or Venezuela."
Can we ever truly be a colorblind society or will we forever have to listen to garbage like this?

On another matter, my U.S. Census questionnaire came in today's mail.  There are only seven questions about each person in the household.  Two of them are about race.  Or maybe only one - and one about Hispanic origin.  The form says that, "For this census, Hispanic origins are not races."

The questions are arranged in a column 11 inches tall.  The two questions about Hispanic origin and race make up 5 of those 11 inches.  The question about race has a category "Black, African Am., or Negro."  Really?  Negro? There is not a category for 'impostor.'

Again, if we are a colorblind society, why do we need this question on the census?  What does it matter to anything what a person's race is?  Seriously - it shouldn't matter.  I think the question should be taken off.  I wonder what Torri Hunter would think.

Saturday, March 13, 2010

BLOODY LUV

Hey, tailgate season is coming up.  I bought a bottle of Jimmy Luv's Bloody Mary Mix - created by a guy right here in Milwaukee.  This is PHENOMENAL stuff!  Hands down the best mix I have ever tasted - even tops my own personal concoction.  Try some.

Friday, March 12, 2010

RADICAL REALIGNMENT

The official Bud Selig Major League advisory committee is floating an idea for realigning the divisions every year "based on geography, payroll, and their perceptions of whether they were contending teams."  It's been a long time since I've heard a more stupid proposal - even out of this group.

Can you imagine a team saying to its fans, "Uhmm, yeah - we don't think we're going to be any good this year so we're going to go over and play in the division with the Yankees and Red Sox so we can be slapped around even more than we would have been otherwise."  How defeatist is that?

If Major League baseball is going to sit down every winter and realign the divisions based on who they think is going to win or lose, what's the point of playing the season anyway?  If you are going to pair the Yankees up every year with a bunch of non-contending teams, how many games are they going to win? 150?  Why would the Yankees even want that? Realign every year based on geography?  What - that's going to change?  The city of Cleveland is moving to Arkansas?

This committee is going to be a complete waste of time and resources if this is the best stuff they can come up with.  If they want to tackle realignment, maybe they should start with the people in the mirror.

Wednesday, March 10, 2010

JASON KENDALL LOVE TRIANGLE... SERIOUSLY

TMZ.com is reporting that Jason Kendall is feuding with his estranged wife Chantel, who happens to be dating Rod Stewart's son, over custody or placement of their kids.  Kendall's ex- is accusing the former Brewers catcher of overusing Adderall.  Neither side is talking about any of the accusations.

Welcome to Milwaukee, Gregg Zaun!!!

NOMAR NOMORE

Nomar Garciaparra retired today.  Didn't his career go by quick?  It seems like only last week that he was a hot-shot rookie, future Hall of Famer for the Red Sox and only yesterday that he was a washed up journeyman.  Today he's done.  Maybe I'm just getting old, but that all seems like it happened much faster than I wish it would have.

Tuesday, March 9, 2010

DISCOVERING THE REAL GREGG ZAUN

In discussing the Brewers backup catcher situation, Anthony Witrado finished this afternoon's blog post with this tidbit:

"Kottaras has shown pop in his bat and is clearly the more offensive-minded of the two, but Treanor has been the better defensive player, showing off a good arm and an ability to block balls in the dirt, which Macha, a former catcher, appreciates.

"The manager wouldn't put one guy ahead of the other at this point because he is waiting to see the kind of catcher Zaun will be during spring training and then he'll select his back-up as Zaun's complement. So if Zaun shows to be a hitter this spring, chances are Treanor gets the nod. If Zaun proves to be more defensive, then it could be Kottaras."
Are you kidding me?  Gregg Zaun has been playing professional baseball for 20 years.  He has nearly 4,000 plate appearances in the Majors and 8,000 innings in the field.  If you don't know what kind of player he's going to be by now you're just plain dense.

I am seriously hoping that this was something Witrado made up to fill space in his article (likely) rather than something that Ken Macha actually said.

UPDATE:

According to Brew Beat, here is what Macha actually said:
"They each give you a little bit different look, Kottaras, watching him take [batting practice], he's got pretty sizeable power when he gets hold of one and he's a left-handed hitter, which is nice to have. ... Treanor, I really like the way he throws the ball and blocks the ball in the dirt. So you've got two kind of different styles, or what they bring to the table is a little different.

"I want to take a look and see what Zaun does as the spring goes on.  That may be a determining factor. I'm open if a guy goes out there and is head and shoulders above everybody."

I wouldn't have had the same take away from that as Witrado did, but in his defense, I have no idea WTF Ken Macha is talking about.

Monday, March 8, 2010

THREE OUT

Major League Baseball is run by hypocrites.  This weekend, three umpire supervisors with almost 100 years of combined experience were let go due to all of the blown calls in last year's playoffs.  This by the same MLB brass who refuses to institute instant replay and automated pitch calling because they want to keep the human element in the game.  Well, you can't have it both ways.  It's time for baseball to open their eyes and use new technology to their benefit rather than making scapegoats of men who have devoted their lives to the game.

THROUGH THE ROOF

David Pinto points out an interesting article about rules for opening and closing roofs in Major League stadiums.  The decision for the position of the roof at the start of the game rests with the home club.  Once the game starts, however, the umpire crew chief has final say as to whether it's moved.  The roof can only be moved once per game.  If it starts open, you can close it, but then you can't reopen it and if it starts closed you can open it but not re-close it.  Same goes for the wall panels in the outfield.

HAWK TALKS BIG PICTURE

USA Today is reporting this week on a series of round-table discussions they are holding to look at ways to improve the game of baseball.  The impressively manned panel includes Brewers reliever LaTroy Hawkins.

Hawkins raised a question to to former umpire Steve Palermo as to whether umpires were influenced by the presence of the QuestTec electronic ball-strike system that used to be in some ballparks.  You would obviously only ask that question if you felt they were.

The series continues all week.  Rather interesting.

Thursday, March 4, 2010

BORN AGAIN

Spring Training Opener today.  I live again...

...and survived another winter.  I'm sure glad this one's over.  Man, they suck more and more every year.

Monday, March 1, 2010

SOUP TO NUTS

I find it interesting that the Brewers will start Jeff Suppan in the exhibition opener on Thursday.

The more I study the roster and read reports out of spring training, the more I feel that Suppan is going to be the odd man out when the Brewers break camp.  Gallardo, Wolf, and Davis are locks for the rotation.  Manny Parra is too valuable of a commodity to not keep in the rotation.  Dave Bush is five years younger and despite a bad-luck bloated ERA, is a better pitcher than Jeff Suppan.  Chris Narveson is showing enough promise that he may even have an inside track on Suppan.  The bullpen is already crowded without him.

I wonder if a small part of why Jeff Suppan is pitching so early in the rotation this spring is so that the Brewers can just get this over with - determine that he just isn't good enough to make the team (if it hasn't been decided already); cut him and move on.

 
Blogged Blog Directory