Statalist


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

Re: st: new package seqlogit available on ssc


From   Maarten buis <maartenbuis@yahoo.co.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: new package seqlogit available on ssc
Date   Wed, 29 Aug 2007 17:32:20 +0100 (BST)

--- Anders Alexandersson <andersalex@gmail.com> wrote:
> I just noticed Martin Buis's new -seqlogit- command which looks very
> interesting. How does it improve on Rory Wolfe's -ocratio- command?
> An obvious improvement is the Stata version, 9.2 versus 5.0. Are
there
> other improvements? Unfortunately, I cannot attend the user meeting
> on September 7.

The main difference with -ocratio- is that -seqlogit- has
post-estimation commands that will decompose the effect of the
explanatory variables on the highest outcome into a effects on passing
transitions and weights assigned to transitions. For instance think of
education: explanatory variables can have an effect on passing the
transitions between levels of education and explanatory variables can
have an effect on the highest achieved level of education. -seqlogit-
has post-estimation tools to link those two types of effects. This only
makes sense if we can meaninfully think of a scale for the highest
achieved level, which is not always the case. If that is not the case
you can still use -seqlogit- but not all postestimation commands will
make sense.

Other differences are:
o -ocratio- only models a series of "stay or leave" decisions, 
  -seqlogit- alows for more general decision trees, e.g. branching
  points (a tracked educational system), choices between more than 2
  options.
o -ocratio- alows you to model the decisions as a logit, probit or
  cloglog, while -seqlogit- only allows the logit. 

I have just added the presentation on -seqlgit- at the Nordic and
Baltic Stata Users Group meeting on Friday September 7th to my website
(http://home.fsw.vu.nl/m.buis/), so you can now see the slides. 

Hope this helps,
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/
-----------------------------------------


      ___________________________________________________________ 
Want ideas for reducing your carbon footprint? Visit Yahoo! For Good  http://uk.promotions.yahoo.com/forgood/environment.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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index