Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

st: Problem while generating limited predictor after spreg


From   [email protected] (Rafal Raciborski, StataCorp)
To   [email protected]
Subject   st: Problem while generating limited predictor after spreg
Date   Wed, 28 Nov 2012 14:32:43 -0600

Lin-Han <[email protected]> has a question involving the calculation of
predicted values after the user-written -spreg- command:

> I ran into a problem while generating limited predictor after spreg...
> I have a dataset with 47,000 observations, and ... when I run this command
> after spreg:
>
> predict yhat, limited
>
> The server ran for more than 60 hours before I forced it to stop, and
> no result is yet generated.

The formulas for spatial predictors are described in section 6.3 of the
working paper by Drukker, Prucha, and Raciborski (2011).  The limited
information predictor involves several matrix-inverse operations, each running
in O(n^3) time.  For n=47,000, my rough calculation puts each matrix-inverse
operation at 67 hours.

-- Rafal
[email protected]

References
----------
Drukker D M, Prucha I R, and Raciborski R. 2011.  Maximum-likelihood
and generalized spatial two-stage least-squares estimators
for a spatial-autoregressive model with spatial-autoregressive disturbances.
Working paper, University of Maryland, Department of Economics, 
http://econweb.umd.edu/~prucha/Papers/WP_spreg_2011.pdf.
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index