[R-sig-Geo] Missing statistics with errorsarlm(method="SparseM")

Roger Bivand Roger.Bivand at nhh.no
Mon Jan 16 19:08:30 CET 2006


On Mon, 16 Jan 2006, Martin Reismann wrote:

> When using errorsarlm with method="SparseM" I encountered that 
> "Asymptotic standard error" and "Wald statistic" are missing in the
> summary. Both are available with errorsarlm method="eigen".

The "SparseM" method is used for large n, when operations on a full matrix
would tax your computer. Computing the information matrix means inverting
an n by n matrix, so statistics relying on the information matrix are not
available with this method. If you must have them for large n, you need
more RAM and possibly a 64 bit box, but in practice if you have many n,
the likelihood ratio will tell you what you need to know anyway.

> 
> Any suggestions?
> 
> Best wishes,
> Martin Reismann
> 
> ---
> Martin Reismann
> Institut fuer Wirtschaftsgeographie und Geoinformatik
> Wirtschaftsuniversitaet Wien
> Nordbergstrasse 15, 4. Stock, Kern A
> A-1090 Wien
> 
> EMail: Martin.Reismann at wu-wien.ac.at
> Tel +43-(0)-1-31336-5720
> Fax +43-(0)-1-31336-703
> 
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> 

-- 
Roger Bivand
Economic Geography Section, Department of Economics, Norwegian School of
Economics and Business Administration, Helleveien 30, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
e-mail: Roger.Bivand at nhh.no




More information about the R-sig-Geo mailing list