On Thu, 30 Apr 2009, Danlin Yu wrote:
Michael:
For the SARLM objects (be it lag or error), the p-values are replaced by the
calculated z-values, and significance tests follow similar ways as in using
the p-values.
Hope this helps.
Cheers,
Danlin
Loechl Michael ??:
Dear list,
is there a way to access the p-values of the coefficients in a
sarlm-object?
Try:
library(spdep)
data(oldcol)
COL.lag.eig <- lagsarlm(CRIME ~ INC + HOVAL, data=COL.OLD,
nb2listw(COL.nb, style="W"))
summary(COL.lag.eig)$Coef
summary(COL.lag.eig)$Coef[,4]
that is, get them from the object returned by summary() of the sarlm
object for the regression coefficients. For rho, you have the LR test
anyway, at:
c(summary(COL.lag.eig)$LR1$p.value)
(inside c() to drop unneeded attributes), and if method="eigen", you also
have the p.value of the Wald statistic, which is the same as the
asymptotic test on rho, even though computed differently:
c(summary(COL.lag.eig)$Wald1$p.value)
Does that give you what you need?
Roger
Any hint is appreciated.
Best regards,
Michael
[[alternative HTML version deleted]]
_______________________________________________
R-sig-Geo mailing list
[email protected]
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: [email protected]
_______________________________________________
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
