model{
### likelihood: joint distribution of y
for (i in 1:n)
{p[i]<-1/exp(theta[i])
y[i]~dnorm(0,p[i])
}
### prior distributions
phi1~dbeta(20,1.5)
phi<-2*phi1-1
mu~dnorm(0,0.01)
itau2~dgamma(2.5,0.025)
tau<-sqrt(1/itau2)
theta0~dnorm(mu,itau2)
thmean[1]<-mu+phi*(theta0-mu)
theta[1]~dnorm(thmean[1],itau2)
for (j in 2:n)
{thmean[j]<-mu+phi*(theta[j-1]-mu)
theta[j]~dnorm(thmean[j],itau2)
}
}
#data
list(n=19,y=c(5.917,6.0587,5.9334,5.8906,5.8189,6.0395,5.9027,6.0142,6.468,6.3844,6.4806,6.7442,6.9832,9.3499,9.1096,9.0589,9.1446,9.5877,8.1597))