Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!linus!philabs!cmcl2!harvard!seismo!hao!noao!amd!pesnta!pyramid!decwrl!decvax!bellcore!ulysses!cbosgd!ukma!david
From: david@ukma.UUCP (David Herron, NPR Lover)
Newsgroups: net.news
Subject: Re: Chuq on Statistics
Message-ID: <2948@ukma.UUCP>
Date: Wed, 26-Mar-86 00:43:44 EST
Article-I.D.: ukma.2948
Posted: Wed Mar 26 00:43:44 1986
Date-Received: Mon, 21-Apr-86 00:25:20 EST
References: <2019@hao.UUCP>
Reply-To: david@ukma.UUCP (David Herron, NPR Lover)
Organization: U of KY Mathematical Sciences
Lines: 50

In article <2019@hao.UUCP> woods@hao.UUCP (Greg Woods) writes:
>...
>> How would you recommend  improving the data then?
>
>  Two ways: the best would be to PROPERLY select a subset of the net to
>respond to the survey; this is probably impossible. Secondly, a more
>standardized program (I have twice before suggested a C program; that you
>have conveniently ignored this shows that you haven't really listened to
>a thing I've said in your haste to make me look bad). I suppose a third
>way would be to think up some way to encourage more people who CAN respond
>to the current survey to do so. No, I don't have all the answers, but that
>isn't a criteria for pointing out flaws in the current procedure.

Why do you keep suggesting C programs?  I don't understand.  I *wrote*
large portions of arbitron, I *know* how much easier it was to write
the report generator with awk than it would in C.  (And I'm a very
accomplished C programmer as well).  Sure the result would run faster
but the shell script is 1) easier to understand/write/maintain, 
2) only run once a month (or less often), and 3) smaller, both in
source and executable.

Be that as it may, I'm convinced that it's useful to know who is 
reading the newsgroups.  When I wrote my version I was wanting to
make an informed decision as to which newsgroups to cut due to phone
bill problems, and I didn't have a good idea which newsgroups were
being read.  [oooh.. I just realized something about arbitron...
it only works with 2.10.2 and above, which keeps everybody else from
responding].  

I do agree tho that until we have large portions of the net responding
then the data isn't all that correct.  But the first returns are rather
interesting.


If a newsgroup isn't read on half the machines on the net, then
why should the net transport it everywhere?


(One answer is so that new users at each site can have a chance
to start reading that newsgroup... but that isn't the answer
I'm interested in... there's still another "49%" of the net
that doesn't read that newsgroup.)
-- 
		Gone to New Orleans for Spring Break!!!

Pressing business requiring postmaster attention can be brought
to the attention of my substitute by mailing to postmaster@ukma
(or postmaster@uky.csnet).
--
David Herron,  cbosgd!ukma!david, david@UKMA.BITNET, david@uky.csnet