Die­ses wun­der­volle Paper—aus der Reihe Maths is Music & Sta­tis­tik—für den Sta­tis­tik­un­ter­richt bzw. die Lehre von Sta­tis­tik an der Uni machte mei­nen Mor­gen: Dick de Veaux—Math is Music—Stats is Lite­ra­ture Stats is Lite­ra­ture (pdf)

George E.P. Box:

All models are wrong– but some are useful“

Sta­tisti­ci­ans, like artists, have the bad habit of fal­ling in love with their models“

Dick de Veaux in Math is Music—Stats is Lite­ra­ture Stats is Lite­ra­ture (pdf):

But, sta­tisti­ci­ans love models–because they are wrong.

What do we focus on?

resi­du­als! […]

Is Sta­tisti­cal Thin­king Unnatural?

  • We haven’t evol­ved to be Statisticians.
  • Our stu­dents who think Sta­tistics is an unna­tu­ral sub­ject are right. This isn’t how humans think naturally.
  • But it is how humans think ratio­nally. And it is how sci­en­tists think. This is the way we must think if we are to make pro­gress in under­stan­ding how the world works and, for that mat­ter, how we our­sel­ves work.

[via Sta­tisti­cal Mode­ling, Cau­sal Infe­rence, and Social Sci­ence]

Verwandte Artikel

Post a comment

RSS Feed Amy Welt Amy @ Twitter Amy @ tumblr