Re: st: sppack [was: SSPACK]

[Ashley Arnio <ana05@fsu.edu>]

Thank you! This was so helpful!

Also, are there any plans to include a k-nn matrix in the near future? 

----- Original Message -----
From: rraciborski@stata.com
Date: Thursday, March 31, 2011 10:51 am
Subject: st: sppack [was: SSPACK]
To: statalist@hsphsun2.harvard.edu

> Ashley Arnio ana05@fsu.edu asked about using the user-written -<BR>> spmat- command
> to create spatial-weighting matrices with weights that are 
> inversely related to
> the square distances between the spatial units:
> 
> > Is it possible to create an inverse distance squared spatial matrix
> > using 'spmat'?
> 
> I will illustrate with the ancilliary pollute.dta dataset that 
> comes with the
> sppack suite.
> 
> First, create an spmat object containing an inverse-distance 
> spatial-weighting
> matrix
> 
>  . use polltue, clear
>  . spmat idistance dobj longitude latitude, id(id) 
> dfunction(dhaversine)
> Now the spatial-weighting matrix, call it W, is contained in the 
> spmat object
> dobj.  Ashley wishes to square each element of W.  To do so, we 
> extract the
> matrix from the spmat object into Mata memory and perform the desired
> calculation
> 
>  . spmat getmatrix dobj W id
>  . mata: W = W:^2
> 
> Now we put the transformed matrix back into the spmat object
> 
>  . spmat putmatrix dobj W id, replace
> 
> This technique is illustrated in the working paper 'Creating and 
> managingspatial-weighting matrices using the spmat command', 
> available at
> http://econweb.umd.edu/~prucha/Papers/WP_spmat_2011.pdf.
> 
> --Rafal
> rraciborski@stata.com
> *
> *   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/
> 

*
*   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/