Newsgroups: comp.ai.fuzzy,sci.stat.math
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!uhog.mit.edu!rutgers!goclenius.rutgers.edu!dziuxsolim.rutgers.edu!uunet!pipex!swrinde!howland.reston.ans.net!vixen.cso.uiuc.edu!usenet.ucs.indiana.edu!news.cs.indiana.edu!umn.edu!hardy
From: hardy@umnstat.stat.umn.edu (Michael Hardy)
Subject: Re: Fuzzy theory or probability theory?
Message-ID: <D096vx.Epw@news.cis.umn.edu>
Sender: news@news.cis.umn.edu (Usenet News Administration)
Nntp-Posting-Host: dec-47.stat.umn.edu
Organization: School of Statistics, University of Minnesota
References: <94Nov29.133132edt.774@neuron.ai.toronto.edu> <1994Nov30.212130.5001@decan.gate.net> <3bkebd$3hu@usenet.srv.cis.pitt.edu>
Date: Sat, 3 Dec 1994 21:13:10 GMT
Lines: 70
Xref: glinda.oz.cs.cmu.edu comp.ai.fuzzy:3538 sci.stat.math:3475

In article <3bkebd$3hu@usenet.srv.cis.pitt.edu> bogdan@neuronet.pitt.edu writes:


>The main point of the text below is whether or not we should make distinction
>between "statistics" and "probability". I think yes!

	[snip]

>It is very tempting to mix "statistics" with "probability" ;-)
>Maybe we should start making distinction between the two?


	Everyone's already been distinguishing between the two all along.
What planet have you been on?  Math departments have lots of probabilists
who know nothing about estimation, confidence intervals, hypothesis testing,
sufficiency, regression, design of experiments, sampling, the whole frequent-
ist versus Bayesian controversy, etc.  Every statistician knows about all of
these things; many probabilists do not.


>This is very important point! I believe that "probability" does NOT equal
>"statistics". Namely, "statistical distribution" does NOT equal "probability
>distribution" !!!

	[snip]

>"Statistical distribution" comes about when somebody wants to analyze
>a collection of samples with respect to some attribute of interest,
>e.g. height.

	[snip]

>"Statistical distribution" becomes "probability distribution" ONLY when
>we want to use it to PREDICT the height of a person that is either
>selected at RANDOM from the population, or that will appear somewhere at
>RANDOM.


	As a Bayesian I regard "probabilities" as epistemic and not intrinsic.
Just what you mean by "statistical distribution" is impossible to tell from
your vague statement.


>"Statistical distribution" per se has NOTHING to do with RANDOMNESS.


	Nor does "probability distribution" if one treats probabilities as
epistemic.


>It should be noted that "statistics" is _static_ since all data IS available.
>(i.e. "statistical distribution" IS available)


	Statistical inference is inductive.  If all the data were available,
everything statisticians do would be irrelevant to the problem.  You ought
to learn how these terms are used before you publicly disagree with the way
you _imagine_ that people use them.


>So what? Why "creating" this distinction?


	Mike Hardy

-- 
Michael Hardy			"Free will is located in or near
School of Statistics		 the anterior cingulate sulcus."
University of Minnesota
hardy@stat.umn.edu				- Francis Crick
