Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!hookup!swrinde!howland.reston.ans.net!news.sprintlink.net!redstone.interpath.net!sas!mozart.unx.sas.com!saswss
From: saswss@hotellng.unx.sas.com (Warren Sarle)
Subject: Re: NN Vs Stats......
Originator: saswss@hotellng.unx.sas.com
Sender: news@unx.sas.com (Noter of Newsworthy Events)
Message-ID: <D2H8rC.Ars@unx.sas.com>
Date: Mon, 16 Jan 1995 02:40:24 GMT
References: <1995Jan11.145719.1@ulkyvx.louisville.edu> <3f9r6i$imn@newsbf02.news.aol.com> <3fa1j6$1kf@usenet.INS.CWRU.Edu> <3fbctt$43b@ixnews2.ix.netcom.com>
Nntp-Posting-Host: hotellng.unx.sas.com
Organization: SAS Institute Inc.
Lines: 29


In article <3fbctt$43b@ixnews2.ix.netcom.com>, JZeanah@ix.netcom.com (Jeff Zeanah) writes:
|> ...
|> I very good comparison, but don't we need to mention:
|>         * NN allow for better modeling under conditions of interaction.
|>         * NN allow the impacts of inputs to vary over the solution
|>           space.
|>
|> Also this does not address an observation for experience that NN usually
|> fit data (obervations) the model has not seen better than Stats.

Comments so totally off-the-wall as this lead me to suspect that
people are still confusing statistics with _linear_ regression and
discriminant analysis. That is worse than confusing neural nets with
the original perceptron. Try some of these books for a taste of what
else is covered in the statistical literature:

   Haerdle, W. (1990), _Applied Nonparametric Regression_, Cambridge
   Univ. Press.

   Scott, D.W. (1992), _Multivariate Density Estimation_, Wiley.

   Seber, G.A.F and Wild, C.J. (1989) _Nonlinear Regression_, Wiley: NY.

-- 

Warren S. Sarle       SAS Institute Inc.   The opinions expressed here
saswss@unx.sas.com    SAS Campus Drive     are mine and not necessarily
(919) 677-8000        Cary, NC 27513, USA  those of SAS Institute.
