Re: st: asmprobit, problems with correlation patterns

["Barbara Hanel " <Barbara.Hanel@wiso.uni-erlangen.de>]

Hallo Rich,
yes, the eink-variable contains indeed quite large values compared 
to AB. I will scale it down and try again. -eink- is not constant over 
many cases, but the values for one alternative are a constant 
proportion of the values for another alternative. Perhaps that might 
be part of the problem? I will see if I can do anything about that too.
 
Unfortunately I have to wait some days until I can try your 
suggestions, so I can not tell you within the next two weeks if the 
changes were successful. But I wil make up for that as soon as 
possible :-)

Thank you so much for your help!
Barbara  


Am 23 Apr 2007, um 13:47 hat Richard Gates geschrieben:

Barbara,

When you run the model using only the -eink- variable make sure
you include the constants too (do not use -noconst-).  From your
one output listing it looked like they are important.  For that 
matter leave in the -AB- c-s variable.  It looks like it is 
important.

I noticed the scale of the coefficient for -eink- is quite small.

altern       |
        eink |    .000631   .0001332     4.74   0.000       .00037  

I take it that the values in -eink- are large in magnitude.  You
may have a scaling issue.  You might try to scale down -eink-
so that it has the same order of magnitude as the -AB- variable

How variable is the data in the -eink- variable? Is it constant for a
majority of the cases? I suspect it not, but since it is the only a-s
variable that you have and I cannot see the data, it is a question that
comes to mind.

If all else fails and your data is not proprietary, I would not mind
taking a look at your problem.


-Rich

On Mon, 2007-04-23 at 17:53 +0200, Barbara Hanel wrote:
> 
> 
> ______________________________________________________________________
> 
> Hallo Rich,
> In the first run I tried to estimate the model just with the a-s-
> Variable "eink" - it doesn´t work too. In fact the model converged,
> but estimated a correlation coefficient of exactly -1. Furthermore, I
> got extremly large standard errors for the variance parameter. (It was
> a specification with only 3 destination states, so there was only one
> covariance parameter beside the variance parameter.)
> I´t seems to me to be a similar problem like in the model with 4
> destination states and a correlation coefficient of _exactly_ -0.5
> But I just don´t know what it in fact could be.
> That problem even persists only with the as-variable.
> 
> I defined the restricted pattern primarily because I hoped it would
> improve the estimation compared to the full model, because there are
> less parameters to identify. So I have even less hope to find a
> solution with the default option.
> 
> 
> I hope I don´t waste too much of your time...
> 
> Thanks a lot,
> Barbara


-- -- -- -- -- -- -- -- -- -- -- -- -- -- 
Dipl.-Volksw. Barbara Hanel
FAU Erlangen N�rnberg
Lehrstuhl f�r Statistik und empirische Wirtschaftsforschung; Prof. Riphahn, 
PhD
0911/5302-258
Lange Gasse 20
90403 N�rnberg
barbara.hanel@wiso.uni-erlangen.de 

*
*   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/