December 2002 comp.lang.* stats

[Laura Creighton]

> In message <3E32E5D6.82887F98 at engcorp.com>, Peter Hansen wrote:
> > "Aaron K. Johnson" wrote:
> > > 
> > > A person is what counts as a 'unique poster'. A message ID alone would no
> t
> > > measure the 'user base' factor "im interested in.
> > > 
> > > Spam is still a problem to consider. It's not perfect yet.......
> > 
> > Spam is probably a problem best ignored.  It would probably
> > affect all those groups equally anyway.
> > 
> > -Peter
> 
> I agree. Plus, I'm not interested in working THAT hard to be that
> anal-retentive about data which some would argue is still vague enough to be
> discounted.
> 
> -Aaron. 

Just FYI -- I am aware this is something that you are mostly doing for
fun, and don't want to spoil it for you -- but you mentioned that you
wanted to be 'more scientific' about this.  This question -- do
I bother with this data?  is it significant?  is the meat of the
'is what I am doing science' question.  I also want to check to make
sure that you are aware that 'I don't know the factors which contribute
to having X in set Y' or even 'Nobody knows' or 'It is impossible to
know' implies 'it will affect all sets equally'.  That belief is bad
science.

Have fun, thanks for the posts,
Laura Creighton