Biased umpiring?

[George_Foreman]

What nonsense. This same type of human behavior is observed in hundreds of other studies. In fact, it's a well known result called the "Hawthorne effect" in social research. When people are observed and know they are being observed, they often alter their behavior to conform to expectations. The results found are exactly what any good social scientist in this field would have expected based on decades of prior research.

If you really think you can write a paper with evidence supporting the other side, be my guest. I'm always willing to be convinced by good evidence. Since you can't even correctly understand the paper at hand, however, I'm eager for the hilarity that would result.

Well said, and I applaud your effort to explain this stuff to people who obviously have minimal experience with statistical analysis. The results here are almost identical to the results from the basketball study which, despite the NBA's vicious (and baseless) attacks, was an accurate and well-done study.

Also not that the authors of this study aren't out to say that this is a major problem. In fact, I would say that their results say the opposite, given that one bad call in 100 pitches is probably a very good night behind the plate.

[IllinoisBandit]

Ya, it's pretty unreasonable to question a study that hasn't even been published yet and hasn't been subjected to peer review.

What this paper does is state an observation of an absolutely TINY phenomena.
Statistics can be manipulated - to get headlines in major publications, as this study has - resulting in outlandish headlines including phrases like "umpires are biased". To make a sweeping claim like that based on this study is premature at best.

See:
Observer-expectancy effect
Publication bias
Confirmation bias

[GotowarMissAgnes]

Ya, it's pretty unreasonable to question a study that hasn't even been published yet and hasn't been subjected to peer review.

What this paper does is state an observation of an absolutely TINY phenomena.
Statistics can be manipulated - to get headlines in major publications, as this study has - resulting in outlandish headlines including phrases like "umpires are biased". To make a sweeping claim like that based on this study is premature at best.

See:
Observer-expectancy effect
Publication bias
Confirmation bias

I don't think it's unreasonable to question a study, published or unpublished. However, if you are going to question it, you ought to read it and raise legitimate questions about the research.

You haven't questioned the study. You've made ridiculous ad hom attacks.

The people that have questioned the study did so either without even reading the paper or else misinterpreted the study and its methods.

Question away, but do your homework first. Sure, statistics can be used to mislead. Show how that has been done in this case, rather than make allegations without any logic or evidence.

The so-called "tiny" effect cumulated over the hundreds of thousands of pitches thrown each year leads to an impact that is worth 2-4 wins from a team's point of view and hundreds of thousands of dollars from a player's point of view. That's the nature of baseball. It's a game of inches and "tiny" factors mean the difference between a home run and weak ground ball or winning the pennant and sitting at home in October.

[WharfRat]

Sorry to dredge this up again, but The Hardball Times had a worthwhile story today on this topic.

http://www.hardballtimes.com/main/article/are-umpires-racist/

[IllinoisBandit]

Dare I claim victory?

Personally, I think the fault lies neither with the authors of the paper nor with the people that believe it.
Boo on Time for giving it premature national exposure without allowing it to run it's course of peer scrutiny and validation. Very poor journalistic practice IMO.

[GotowarMissAgnes]

Dare I claim victory?

Personally, I think the fault lies neither with the authors of the paper nor with the people that believe it.
Boo on Time for giving it premature national exposure without allowing it to run it's course of peer scrutiny and validation. Very poor journalistic practice IMO.

Before claiming victory, you might carefully read some of the blogs:

http://www.insidethebook.com/ee/index.p ... n_i_think/

Given that the people criticizing the study honestly confess their ignorance of some of the basic statistical methods used, such as the difference between a probit and logit method, as well as complete ignorance of what a fixed effect is, I'd hardly be inclined to trust their assessment of the study.

Furthermore, as many on the Sports Economist point out, wide exposure, even before peer-reviewed publication, is a GOOD thing. It causes good researchers to get a wide variety of comments and criticisms, allowing them to further improve the analysis.

Maybe some people want to go back to the olden days, where no one saw a paper before it was published, except three or four reviewers.

Me, I like the idea that papers are widely circulated among both the academic and nonacademic communities, because it generates a vigorous discussion from a huge variety of perspectives, raising al sorts of ways to improve the existing studies, as well as ideas about new studies that ned to be done.