Newsgroups: sci.lang
Path: cantaloupe.srv.cs.cmu.edu!bb3.andrew.cmu.edu!newsfeed.pitt.edu!scramble.lm.com!news.math.psu.edu!news3.cac.psu.edu!howland.erols.net!www.nntp.primenet.com!nntp.primenet.com!netcom.com!petrich
From: petrich@netcom.com (Loren Petrich)
Subject: Re: Ruhlen's "On the Origin of Languages": a Review (I)
Message-ID: <petrichDxnHHG.GI9@netcom.com>
Organization: NETCOM On-line Communication Services (408 261-4700 guest)
References: <4vvkje$guk@news.xs4all.nl> <5143ei$ejv@netsrv2.spss.com> <petrichDxJyr8.7rM@netcom.com> <519d00$871@netsrv2.spss.com>
Date: Fri, 13 Sep 1996 02:56:03 GMT
Lines: 27
Sender: petrich@netcom14.netcom.com

In article <519d00$871@netsrv2.spss.com>,
Mark Rosenfelder <markrose@spss.com> wrote:

>>	Is this reasoning good, or is there some hole I've missed?

>Scott calculated that the probability of getting 13 matches among 31
>language families is about 42%.  And that's not even taking into account
>that one can choose which languages to use from within each family.

>I'd also apply a maxim from programming: garbage in, garbage out. ...

	Which applies to Scott's calculation -- what was his probability 
of an *individual* match?

	I myself will continue work on estimating multi-match 
probabilities; one thing I will have to work on is including the effect 
of synonyms.

	[a whole lot of mock long-range comparisons deleted...]

	But that begs the whole comparison -- how can one do comparison 
at all?
-- 
Loren Petrich				Happiness is a fast Macintosh
petrich@netcom.com			And a fast train
My home page: http://www.webcom.com/petrich/home.html
Mirrored at: ftp://ftp.netcom.com/pub/pe/petrich/home.html


