[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]
2023-11: Warosu is now out of extended maintenance.

/sci/ - Science & Math


View post   

File: 108 KB, 400x381, 1412974688906.png [View same] [iqdb] [saucenao] [google]
8425690 No.8425690 [Reply] [Original]

Isn't basic statistics pretty much set in stone at this point? How is it that Andrew gelman can have a gigantic blog that criticises uses of statistics in science? I doubt he's talking crap, so how the hell is everyone else fucking up so much?

>> No.8425703

>>8425690
simple, they work in the less rigorous """sciences""" such as biology, psychology, sociology, and economics. To because a researcher in these fields requires fairly little in the way of mathematical background and they get spoonfed significance test algorithms that only work in a very rigid set of circumstances.

Naturally research is not always done according a set methodology and the lack of deep understanding of statistics leads to the basic errors highlighted by Prof. Gelman.

The problem is that when the algorithmic approach to significance testing doesn't work they simply don't understand enough to know why.