Print

Print


Dear BUGS users,
 
I am new to WinBUGS and am wondering if anyone can help me.  I am trying to add random spatial effects to a logistic model of daily nest survival for wetland birds.  Currently I am trying to use spatial.exp to introduce the random effects, but keep getting error messages that say "undefined real result".  I've adjusted the priors and initial values numerous times, but nothing seems to work.  I should say that I am analyzing 11 discrete wetland patches, and am only interested in within patch spatial autocorrelation.  I have tried analyzing one patch at a time and that doesn't seem to work either.  Does anyone have any advice on what to do?
 
Here's the model I am trying to run:
 
model{
 tau ~ dgamma(0.1,0.1)
 phi ~ dunif(0,100)
 b0 ~ dnorm(0.0,0.1)
 b1 ~ dnorm(0.0,0.1)
 b2 ~ dnorm(0.0,0.1)
 for (i in 1:n){
  noise[i] ~ dnorm(0.0, taunoise)
  fate[i] ~ dbin(p[i],1)
  p[i]<-pow(exp(lp[i])/(1+exp(lp[i])),ed[i])
  lp[i]<-b0 + b1*buffer[i] + b2*predaor[i] + yeareffect[yr[i]] + wetlandeffect[wl[i]] + s[i]
  mu[i]<-0
  }
 
 s[1:n] ~ spatial.exp(mu[],x[],y[],tau,phi,1)
 
 for(t in 1:nyears) {
        yeareffect[t] ~ dnorm(0.0, tauyear)
        }
     
 tauyear~dgamma(0.1, 0.1)
       sdyears <- 1/sqrt(tauyear)
 
 for(s in 1:nwl){
  wetlandeffect[s] ~ dnorm(0.0, tauwetland)
  }
 
 tauwetland ~ dgamma(0.1,0.1)
 sdwetland <- 1/sqrt(tauwetland) 
}
 
Note, I only have problems when running the model with the spatial effects.  Otherwise, everything is fine.
 
Thanks in advance.
 
Sincerely,
 
-Max Post van der Burg
_____________________________
Max Post van der Burg
Graduate Research Assistant
School of Natural Resources
University of Nebraska- Lincoln
202 Natural Resources Hall
Lincoln, NE 68583-0819
Ph- 402-472-0508
------------------------------------------------------------------- This list is for discussion of modelling issues and the BUGS software. For help with crashes and error messages, first mail [log in to unmask]

To mail the BUGS list, mail to [log in to unmask] Before mailing, please check the archive at www.jiscmail.ac.uk/lists/bugs.html Please do not mail attachments to the list.

To leave the BUGS list, send LEAVE BUGS to [log in to unmask] If this fails, mail [log in to unmask], NOT the whole list