Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Spatial estimation techniques on panel data - spatreg possible?


From   Austin Nichols <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Spatial estimation techniques on panel data - spatreg possible?
Date   Wed, 18 Feb 2009 11:45:35 -0500

See
http://www.stata.com/meeting/snasug08/drukker_spatial.pdf
esp. the last line on page 30.

On Wed, Feb 18, 2009 at 11:10 AM,  <Phil1899@gmx.de> wrote:
> Hello,
>
> I am new on the subscriber list. I currently try to estimate a model explaining bilateral multinational activity which is augmented by a spatial lag. My problem is that I want to use panel data and that the spatreg commands only work for cross-sections. I saw an earlier question in this context on Statlist which was not further treated due to the lack of theory. However, there are a number of economic papers which have already applied spatial estimation techniques on panel data.
>
> The basic problem is that the weighting matrix is constructed according to the observations of one year only. I am now wondering whether it is possible to somehow tell STATA that the vector of the dependent variable should be multiplied with the weighting matrix for each year seperately?
>
> Another possibility would be to manipulate the data in this way before loading it to STATA. However, then it is obviously not possible to use the spatreg commands anymore.

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index