Re: st: reldist -- relative distributions

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Mon, 12/4/10, Tony wrote:
> I probably wasn't finished, not yet anyway. People
> sometimes show up at meetings and "proudly" annouce
> programs they hadn't finished. Not the first time
> this happened.

There is nothing wrong with that, it is entirely 
consistent with the general nature of a scientific 
conference: From the point of view of a presenter, 
the most useful stuff to present is stuff that isn't 
quite finished, as any comments you get from the 
audience are most useful at that stage. These 
comments are no longer as useful once the work is 
finished and submitted (e.g. to the Stata Journal). 

The consequence of this is that not everything that 
is presented at a Stata Meeting will make it to SSC 
or the Stata Journal, either because presenter had to 
do other things (remember that writing Stata 
programs is for most authors voluteer work), or 
because they found that the method they proposed 
contained a fundamental error (this happend to me 
once). I realise that this can be frustrating for 
someone who is looking for a solution to his problem, 
thought he found the solution is such a presentation, 
and is than dissapointed. But IMHO discouraging this 
practice would be much worse, as discussing ideas is 
the very reason why we hold these meetings.

-- Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/