[R] [OT] "normal" (as in "Guassian")

Ben Bolker bolker at ufl.edu
Sun Mar 2 17:59:53 CET 2008


roger koenker <roger <at> ysidro.econ.uiuc.edu> writes:

> 
> A nice survey of this territory is:
> 
>
http://books.google.com/books?id=TN3_d7ibo30C&pg=PA85&lpg=PA85&dq=stigler+normal+oxymoron&source=web&ots=OwGhmnDk3O&sig=J7ou_L8-_Mu4L14c3KJAhefrD4I&hl=en
> 
> I particularly like the phrase:  "[normal] is in this respect
> a rare one-word oxymoron."
> 

   Apparently (at least according to the all-knowing Internet),
these are "contronyms" ( http://everything2.com/index.pl?node_id=1217396 ).
My favorite statistical example is "overdispersion", which in most of
statistics means "more variance than expected", but in spatial statistics
is also used to mean "more regular than a random distribution", i.e.
"less variance than expected" (!!)

  cheers
    Ben



More information about the R-help mailing list