Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

st: Spatial lag regression


From   Haniza Khalid <haniza.khalid@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Spatial lag regression
Date   Wed, 14 Jul 2010 00:27:24 +0800

Hello all,

I am running a hedonic price model with sales data over a large
geographical area and hence would like to test for spatial dependence.
My LM tests results suggested that I should use a spatial lag model.
My questions are :

1. If I use the spatreg command, the results would not show R-squared
or adjusted R-squared values? Why is that? Any suggestions how I can
present a comparison of OLS and Spatial ML models in terms of
coefficient values etc. as well as goodness of fit?


2. How can I write a code for a spatio-temporal regression function in
Stata to suit

                 "y=a+bX1+bX2+bX3+rho*z*y"

where rho stands for the spatial lag coefficient; matrix Z should be
obtained from the Hadamard product of matrices W and T. Matrix T is
lower triangular and comprises a null matrix interspersed with blocks
of ones identifying for each observation sold in the same year or the
year before. Basically, the model implies that y or price is affected
only by neighbouring parcels sold in the same year or the year before,
and not in the years too far back or in the future.

 Please kindly suggest some directions for all or any part of the
questions above. Thank you very much.

Regards,
H Khalid

*
*   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   |   Site index