Re:P-Values are not Error Probabilities (2003) [pdf]
by return0 on Monday April 06, 2015 @06:23PM
(#9331054)
Amen for #2! It's like the entire field of biology is an endless quest for low p-values, regardless if the hypothesis is even interesting. It's like people are not interested to think, they just want to publish something significantly differnt.
[ Parent
| on HN ]
Re:P-Values are not Error Probabilities (2003) [pdf]
by cl42 on Monday April 06, 2015 @06:47PM
(#9331143)
haha, Sociology as well -- especially now that the web provides huge amounts of behavioral data.
I much prefer how machine learning folks tend to approach predictive accuracy, though I guess that's not quite the same as understanding relationships between specific variables while controlling for others.
Re:P-Values are not Error Probabilities (2003) [pdf]
by sdenton4 on Monday April 06, 2015 @07:09PM
(#9331217)
There is a notion of 'feature importance,' which especially comes up in decision trees and random forests, giving a notion of how much a particular feature contributes to the overall prediction. It seems like combining predictive power with feature importance would be an interesting alternate route to demonstrating important correlations. (For example, maybe a model predicts lung cancer with 90% precision, and 'is_smoker' has a 80% feature importance.) Of course, these importances depend a lot on the other features used by the model! If you include a lot of junk features and/or exclude other important features, the importance of your pet feature will shoot up.
Re:P-Values are not Error Probabilities (2003) [pdf]
by cl42 on Monday April 06, 2015 @09:24PM
(#9331533)
Hmm, interesting -- I never considered the idea of including junk features to bias model's preferences of whatever theoretically ambiguous idea you're trying to promote. That's actually brilliant.
Re:P-Values are not Error Probabilities (2003) [pdf]
by mbq on Tuesday April 07, 2015 @06:53AM
(#9333032)
Shameless plug; I'm a co-author of a method that leverages adding artificial junk features and removing original ones that are likely nonsense to approximate the set of all features that are relevant to the problem (rather than standard make best model, which may be pretty deceiving). https://m2.icm.edu.pl/boruta
Re:P-Values are not Error Probabilities (2003) [pdf]
by shasta on Monday April 06, 2015 @06:56PM
(#9331173)
Shoes reduce cholesterol.
Re:P-Values are not Error Probabilities (2003) [pdf]
by cl42 on Monday April 06, 2015 @09:23PM
(#9331529)
And aren't ice cream sales dependent on murder rates?
Re:P-Values are not Error Probabilities (2003) [pdf]
by copperx on Wednesday April 08, 2015 @03:31AM
(#9339205)
Did you just discredit Freakonomics?
Re:P-Values are not Error Probabilities (2003) [pdf]
by Sharlin on Tuesday April 07, 2015 @08:43AM
(#9333519)
> they just want to publish something
What's going on in the academia is a classical example of perverse incentives. If your career depends on churning out soul-crushingly bad or insignificant papers that fulfill some superficial criteria of "scienceness" then that's what you'll do. It's dangerously close to cargo cult science.