Re: st: RE: Positivity

["Teresa Linz" <tlinz@uni-bonn.de>]

Yes that is exactly what I mean. I have heard that this 
reparamrisation is quite complicated in Stata, is that 
right? How can I do it in detail?
Thank you for your answer so far

Teresa



On Tue, 29 Jul 2008 18:49:32 +0100
 "Nick Cox" <n.j.cox@durham.ac.uk> wrote:

> If you mean: How can I ensure that I get positive 
> estimates for
> coefficients I expect to be positive, the answer is to 
> reparametrise in
> terms of logarithms. 
> Otherwise, please expand on this question.
>
> Nick
> n.j.cox@durham.ac.uk 
> Teresa Linz
>
> And I have another question; does anybody know how I 
> could 
> programme positivity for some coefficients in Stata?
>
> *
> *   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/
_______________________________

Teresa Linz, M.Sc.

Junior Researcher

Center for Development Research

Walter-Flex-Str. 3

53113 Bonn

Germany

Tel.: +49 228/73 4962
Fax:  +49 228/73 1869
Internet: www.zef.de
*
*   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/