[R-sig-Geo] Spatial Regression Eigenwert-Matrix

[Roger Bivand]

On Fri, 22 Nov 2013, Jacqueline Schweizer wrote:

>
> # Moran's I Test
> moran.test(reg.lm.bereinigt2$residuals, listw=n.listw.obj, alternative="two.sided", na.action=na.exclude,
> 			zero.policy=TRUE)
>

... and *NEVER* run Moran's I on regression residuals with moran.test(), 
always use lm.morantest() on the fitted model object. The expectation and 
variance of I are defined differently in the two tests, the difference has 
been know about for at least 40 years.

Roger

-- 
Roger Bivand
Department of Economics, NHH Norwegian School of Economics,
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