[Link] On the Height of a Field

21gwern

7[anonymous]

11Mark_Eichenlaub

7[anonymous]

0Mestroyer

0BlazeOrangeDeer

New Comment

I like this blog. Going through some of the archives, I particularly liked:

- http://arcsecond.wordpress.com/2012/04/28/14-billion-cupcakes-or-why-you-dont-know-what-to-do-with-your-life/
- http://arcsecond.wordpress.com/2011/04/29/admissions/
- http://arcsecond.wordpress.com/2011/02/08/late-night-thoughts-on-reading-scientology/
- http://arcsecond.wordpress.com/2010/09/08/flat-priors-and-other-improbable-tales/
- http://arcsecond.wordpress.com/2012/01/30/parables/
- http://arcsecond.wordpress.com/2012/02/07/why-least-squares/
- http://arcsecond.wordpress.com/2009/07/24/answer-archimedes-reloaded/

The title is funny but misleading. I read the article because of my initial confusion, and don't regret it, but please make it more descriptive.

I'm the author - thanks for the feedback. I think you're right that a more-topical title could help. **Edit**: done.

I was referring to the thread title here on LessWrong. I actually chuckled at yours, now I feel bad.

Great article by the way. My first thought was to use a tiltmeter app on a smartphone attached to a long ruler.

The story of how belief is supposed to work is that for each bit of evidence, you consider its likelihood under all the various hypotheses, then multiplying these likelihoods, you find your final result, and it tells you exactly how confident you should be.

You should add, shouldn't you? Not multiply? Because they're mutually exclusive and exhaustive probabilities? If you multiply, your probability would change depending on how finely you broke down the hypotheses.

Mark Eichenlaub posted a great little case-study about the difficulty of updating beliefs, even over trivial matters like the slope of a baseball field. The basic story of Bayes-updating assumes the likelihood of evidence in different states is obvious, but feedback between observations and judgments about likelihood quickly complicate the situation:

Edit:Title changed from "An Empirical Evaluation into Runner's High," the original title of the article, to match the author's new title.