Hi R-floks:
Working in geoRglm, it shows me, according to AIC criterion, that the
non-spacial model describes the process in a better way. It's the first time
that I'm facing up to.
These are my results:
OP2003Seppos.AICnonsp-OP2003Seppos.AICsp
#[1] -4
(OP2003Seppos.lf0.p<-exp(OP2003Seppos.lf0$beta)/(1+exp(OP2003Seppos.lf0$beta)))
#P non spatial
#[1] 0.9717596
(OP2003Seppos.lf.p<-exp(OP2003Seppos.lf$beta)/(1+exp(OP2003Seppos.lf$beta))) #P
spatial
#[1] 0.9717596
It must what have an important influence at kriging, because it shows as
following:
OP2003Sepposbin.krig<-glsm.krige(OP2003Seppos.tune,loc=OP2003Seppospro.pred.grid,bor=OP2003Sepposbor)
#glsm.krige: Prediction for a generalised linear spatial model
#There are 50 or mode advices (use warnings() to see them)
#> warnings()
#Warning messages:
#1: In asympvar(kpl.result$predict, messages = FALSE) ... :
# value of argument lag.max is not suffiently long
#2: In asympvar(kpl.result$predict, messages = FALSE) ... :
# value of argument lag.max is not suffiently long
I don't understand the warnings. Help me, please. What can I do to solve such a
situation?.
[[alternative HTML version deleted]]
_______________________________________________
R-sig-Geo mailing list
R-sig-Geo@stat.math.ethz.ch
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
