FanShot

Statistical Shenanigans (Part 1)

I thought this article about correlation and regression coefficients as applied to baseball statistics was quite interesting. I know Chuck has brought light to this point and will probably agree with this following line by the author (John Beamer): "Correlation and regression coefficients are perhaps the two most abused statistical measures by (baseball) analysts. How often do you see a baseball study quoting a correlation of 0.2, or an R squared of 0.49, and being told that the result is meaningful? Quite often I’d posit. Is it? Some studies say a correlation of 0.3 is strong, others dismiss it. Who is right?" In a fanpost over at Beyond the Box Score, Sky Kalkman, three quarters a way down this thread, (a discussion about coco crisp defensive projections, which is neither here nor there) brings up a valid point regarding variance due to inaccuracy of a measuring statistic (or statistical tool) vs. variance due to (repeatable) skill and variance due to luck, in regards to using UZR defense metric. I've been somewhat concerned at what comes off to me anyways, as an acceptance of UZR (and any defensive metric) as equally valid a statistical measure as EQA or wOBA for that matter at sites like Fangraphs in evaluating a players overall value and using these values to formulate arguments in their articles. Anyone who has picked up a medical or scientific research journal can tell you that correlation coefficients are documented in about all of these published studies to demonstrate the strength of the(se) finding(s). I would like to see it be demonstrated more often in the baseball statistical analysis that I consume.

X
Log In Sign Up

forgot?
Log In Sign Up

Forgot password?

We'll email you a reset link.

If you signed up using a 3rd party account like Facebook or Twitter, please login with it instead.

Forgot password?

Try another email?

Almost done,

Join Let's Go Tribe

You must be a member of Let's Go Tribe to participate.

We have our own Community Guidelines at Let's Go Tribe. You should read them.

Join Let's Go Tribe

You must be a member of Let's Go Tribe to participate.

We have our own Community Guidelines at Let's Go Tribe. You should read them.

Spinner.vc97ec6e

Authenticating

Great!

Choose an available username to complete sign up.

In order to provide our users with a better overall experience, we ask for more information from Facebook when using it to login so that we can learn more about our audience and provide you with the best possible experience. We do not store specific user data and the sharing of it is not required to login with Facebook.

tracking_pixel_9351_tracker