Page 1 of 1

Bayesian spatial model, sampling error

Posted: Thu Jul 13, 2017 7:54 pm
by sinasahebi
I have a problem with my code, multivariate poison with spatial correlation, which is written with Openbugs.

The code can not update samples. Do you have any idea about the problem?

Following you can see the first part of the code. you can find the complete code here. (https://drive.google.com/file/d/0BzwgJ- ... sp=sharing)

model {

# likelihood for (i in 1:407) { HO ~ dpois(lambdaHO) lambdaHO <- exp(rhoHO + betaHO*ln) }

betaHO ~ dnorm (0,0.001)

# CAR prior distribution for spatial random effect: rhoHO[1:407] ~ car.normal(adj[], weights[], num[], tauSp)

for(k in 1:802) { weights[k] <- 1 }

# other priors

tauSp <- pow(sdSp, -2) sdSp ~ dunif(0, 5) }

inits 1

list(betaHO=0,tau=1, sdSp=2 )