model {
  for(i in 1:N) {
		X[i,1]<-1.0 
		#main effects for categories
		X[i,2]<-equals(season[i], 2)				
		X[i,3]<-(rock[i]-mean(rock[]))/(2*sd(rock[]))
		#interactions for categories
		X[i,4]<-(veg[i]-mean(veg[]))/(2*sd(veg[]))
		X[i,5]<-(svl[i]-mean(svl[]))/(2*sd(svl[]))
		X[i,6]<-X[i,2]*X[i,3]
		X[i,7]<-X[i,2]*X[i,4]
		X[i,8]<-X[i,2]*X[i,5]
		X[i,9]<-X[i,3]*X[i,4]
		X[i,10]<-X[i,3]*X[i,5]				
		X[i,11]<-X[i,4]*X[i,5]
		#X[i,12]<-X[i,2]*X[i,9]
		#X[i,13]<-X[i,2]*X[i,10]
		X[i,12]<-X[i,2]*X[i,11]						
	}

	for(i in 1:N){
		Mi[i]~dnorm(mu[i],  tau.exp[i])
		tau.exp[i]<- tau*1/sqrt(exp(X[i,4]*2*delta))
		mu[i]<- inprod(alpha[2:12],X[i, 2:12]) + Loc[location[i]] #+ X[i,4]*Ind.gud[hz[i]]
		e.obs[i]<-(Mi[i]-mu[i])/sqrt(sd(Mi[]))
	}
	for( c in 1 : 2) {
		Loc[c]~dnorm(alpha[1], tau.loc)
	}	
	tau.loc <- 1 / (sigma.loc * sigma.loc)
    sigma.loc ~ dunif(0, 100)
	for (L in 1:12){
		alpha[L]~dnorm(0.0, 1.0E-6)
	}
  delta~dnorm(0, 1E-6)
#delta[2]~dnorm(0.0, 1.0E-6)
	#delta[3]~dnorm(0.0, 1.0E-6)
	tau~dgamma(0.01, 0.01)
	#tau[2]~dgamma(0.001, 0.001)	
	#tau[3]~dgamma(0.001, 0.001)		
	
	#tau.loc~dgamma(0.01, 0.01)
#	tau.Ind.gud~dgamma(0.001, 0.001)
  p.val<-2*(1-step(alpha))
	#Deviance <- -2*sum( l[1:128] )
}