Re:Machine Learning Crash Course: The Bias-Variance Dilemma
by joshuamorton on Monday July 17, 2017 @05:52PM
(#14792574)
The other common example of the same phenomena is a test for a deadly genetic defect with a 1% false positive rate. If the incidence of the defect is .01% and you test positive, its actually more likely that you don't have the disease. (although this can be solved with bayesianism over frequentism).
[ Parent
| on HN ]
Re:Machine Learning Crash Course: The Bias-Variance Dilemma
by gpawl on Monday July 17, 2017 @09:22PM
(#14793694)
This is a pernicious misunderstanding of "frequentism", often found among people who studied statistics mainly by reading comics.
http://web.archive.org/web/20130117080920/http://andrewgelma...
Re:Machine Learning Crash Course: The Bias-Variance Dilemma
by joshuamorton on Tuesday July 18, 2017 @11:40AM
(#14797385)
That's incredibly unnecessary. My understanding of statistics is not derived from comics (and the first time I heard that example was in a statistics course), and the link you post doesn't actually address what I stated. It addresses an actual mistake in the comic, which is a mistake that I didn't make.
Here's Andrew, the author of that blog post:
> Yes, I think it makes a lot of sense to criticize particular frequentist or Bayesian methods rather than to criticize freq or Bayes statisticians.
Which is exactly what I did. There are times when frequentist methods are effective. I just wouldn't use them to tell me that I have a disease.