Statalist


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

RE: st: Importing beta coefficients from other softwares


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Importing beta coefficients from other softwares
Date   Wed, 28 May 2008 17:35:33 +0100

I don't think you are addressing the main point. If you have the data to
do some stuff in Limdep, then it is not clear why you can not read the
data into Stata to do some other stuff in Stata. That should not involve
any programming at all and if there are specific problems with file
formats, then people on this list can advise. It is difficult to help
when your real problem is not clear and your story keeps changing. 

Nick 
n.j.cox@durham.ac.uk 

Yaseen Ghulam

Thanks Richard. I agree with you that one option is to run the routine
in stata. But unfortunately stata does not support some methods which I
am using or will need lot of programming which I am not comfortable. 
To be specific I am interesting in using lincom and nlcom routines. I
feel that if I can bring beta, standard error into stata etc. then I
should be able to use these functions. But I am not sure where to put
these information in stata system file which nlcom can use. Thanks again
for the response.

>>> Richard Williams <Richard.A.Williams.5@ND.edu> 05/28/08 3:17 pm
>>>
At 04:57 AM 5/28/2008, Yaseen Ghulam wrote:

>I have very simple question and would appreciate if someone can help
me.
>I have estimated the model in limdep and want to bring beta
coefficients
>and standard error into stata so that I can perform subsequent
analysis
>e.g. predictions and hypothesis testing in stata where I am more
>comfortable. I want to know how to bring and set up betas' in a way
>where I can do all the tasks (post estimation) which one can do if
the
>model was estimated in stata.

What type of analysis are you doing, and why can't you rerun it in 
Stata?  If it is some kind of technique that Stata can't handle, I am 
not sure that post-estimation commands (e.g. predict) would work
anyway.

Ben Jann's user-written routines eret2 and erepost might possibly be
helpful.

*
*   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