[R-sig-Geo] Working with Poisson distribution (geoRglm)

[Jimmy Neutron]

Hi comRades:
I realized that I'm working with count data (survey in the sea).
My 'geodata' (which I named a2008.posCEROSbin) is such as:       xUTMkm   yUTMkm 'Count'1385 450.1202 1011.425   01386 450.4273 1007.219   01387 450.2584 1011.884   01388 450.1696 1010.261   01389 450.1718 1009.887   01390 450.6981 1004.379   0...
I read the geoRglm structure. What does it mean that I have to make a empiric variogram?. I usually worked with binomial data (Success, No-Success). Then, my empiric variogram was such as:
a2008.posCEROS.spmod<-list(cov.pars=c(1,20),beta=1.0,cov.model="matern",nugget=0,kappa=0.35,family="binomial",link="logit")
Now, I suppose that, with my 'geodata' (which I named a2008.posCEROSbin), my Poisson model should be as following:
a2008.posCEROS.spmod<-list(cov.pars=c(1,20),beta=1.0,cov.model="matern",nugget=0,kappa=0.35,family="poisson",link="logit")
After that, I will generate MCMC simulations, such as:a2008.posCEROS.mcmc<-mcmc.control(S.scale=0.582, thin=10) #mcmc marc of change monte carlo, S.scale
However, when I do:a2008.posCEROS.tune<-glsm.mcmc(a2008.posCEROSbin, model=a2008.posCEROS.spmod, mcmc.input=a2008.posCEROS.mcmc)...I have this sentence:
Error in if (lambda == 0) {: argument has zero length.
I'd like to know where is my mistake. I think that I am not making right my empirical Poisson model.
My goal is to predict how many 'Count' do I have in the whole survey.
Thanks in advance for youR help.
Jimmy M. 		 	   		  
	[[alternative HTML version deleted]]