Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: gologit2


From   Maarten buis <[email protected]>
To   [email protected]
Subject   RE: st: gologit2
Date   Fri, 18 Apr 2008 15:36:52 +0100 (BST)

--- Martin Weiss <[email protected]> wrote:
> Very much apart from the heated discussion in this thread, 

I would not call this thread heated (I read that as there being any
animosity), far from it. Rich and I are both interested in how well
tests for the proportional odds assumption perform, and we are trying
to get a feel for that by exploring a variety of scenarios using
simulation. This process is very much like a brainstorm session: The
first one to speak doesn't have to be right, he is just setting the
proces in motion. I think that that is the status of my first
simulation, it got various useful elements, and Rich and I were
gradually expanding on it, and thus found also found the limitations of
this initial simulation. Normally this process happens behind closed
doors, and you only get to see the final paper, in which it looks like
those brilliant authors immediately saw what the relevant scenarios
are. Now you have had a glimpse into how such papers are really
created. Anyhow, as I should actually be working on my dissertation, I
have told Richard that I won't continue this process till I have
finished my dissertation. 

> could anyone tell me what - list retokenize- does. Cannot find it
> anywhere. -findit list retokenize- does not throw up anything,
either.

This is an extended macro function, which took the macro x, and made
sure every element of x was separeted by only one space. See: 
-help extended_fcn- and -help macrolists-
 
> Furthermore, I would be interested how long Maarten`s original code
> (10,000 reps) a couple of days ago took to execute for you. I ran it
> last night on 2GB Ram, Vista SP1 32-bit, with AMD 64 2.2 GhZ dual
> core under Stata 10.0 MP/2, and it took 7.3 hours (26212 seconds). 

It took a bit more than 11 hours on my relatively old university
computer.

-- Maarten


-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

http://home.fsw.vu.nl/m.buis/
-----------------------------------------


      __________________________________________________________
Sent from Yahoo! Mail.
A Smarter Email http://uk.docs.yahoo.com/nowyoucan.html
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index