Re: Fuzzy Logic


Subject: Re: Fuzzy Logic
From: John Lee P. Holmes (jlh2r@virginia.edu)
Date: Mon Nov 20 2000 - 17:47:55 MET


I recommend the work of Charles Ragin, a sociologist at Northwestern, who
applies boolean algebra and fuzzy set theory to inference in the social
sciences. His work, The Comparative Method, nicely discusses the different
ways discrete methods like Boolean and Fuzzy sets deal with inference in
contradistinction to statistics (in which he is quite well versed). His new
book, which I haven't read yet, Fuzzy-Set Social Science (published June 2000
- check http://www.bestbookbuys.com ), will doubtless answer your question.
But on the boolean stuff in brief he points out that discrete methods treat
cases as wholes whereas continuous variable methods like statistics
disaggregate cases into their variables before recombining. So I think here
(and this is I must caution my less erudite interpretation - I may
misunderstand) there is less of a degrees of freedom problem.

Does that make sense?

 BTW I'm still hoping someone will answer my inquiry regarding whether there
is fuzzy logic plug-in or template for Excel or other spreadsheets available?

Cheers,

John Lee Holmes
Ph.D. Candidate, Department of Government and Foreign Affairs
Research Analyst, Center for Survey Research
University of Virginia

"Mark A. Baldridge" wrote:

> I am still not all that familiar with FL, but in statistics there is a
> fairly formal recognition of degrees of freedom. If you have 10 pieces of
> information, and 10 degrees of freedom, and you calculate a mean, the
> result is a mean plus a data set with only 9 degrees of freedom. You
> cannot make more information than you started with. If you subsequently
> calculate a standard deviation, your sample then only has 8 degrees of
> freedom, as you now also have a mean and a standard deviation calculated
> from the sample set.
>
> In FL, I am less sure about the knowledge of the data when you defuzzify
> the data, and conclude an answer. Do we now think we have more
> information than we had before, since the fuzziness is gone?
>
> Martin Sewell wrote:
>
> > "Fuzzy logic is nothing more than a reformulation of statistical
> > inference and probability theory. No solution can be found that could
> > not be achieved at least as effectively using probability and
> > statistics."
> >
> > Can anyone refute this?

############################################################################
This message was posted through the fuzzy mailing list.
(1) To subscribe to this mailing list, send a message body of
"SUB FUZZY-MAIL myFirstName mySurname" to listproc@dbai.tuwien.ac.at
(2) To unsubscribe from this mailing list, send a message body of
"UNSUB FUZZY-MAIL" or "UNSUB FUZZY-MAIL yoursubscription@email.address.com"
to listproc@dbai.tuwien.ac.at
(3) To reach the human who maintains the list, send mail to
fuzzy-owner@dbai.tuwien.ac.at
(4) WWW access and other information on Fuzzy Sets and Logic see
http://www.dbai.tuwien.ac.at/ftp/mlowner/fuzzy-mail.info
(5) WWW archive: http://www.dbai.tuwien.ac.at/marchives/fuzzy-mail/index.html



This archive was generated by hypermail 2b25 : Mon Nov 20 2000 - 17:50:44 MET