model
{
for(i in 1:N) {
     y[i] ~ dnorm(mu, tau)
     ypred[i] ~ dnorm(mu,tau)        # predicted values 
                                     # (draws from posterior predictive dist'n)
}
mu ~ dnorm(0, .00001)
tau ~ dgamma(.0001, .0001)
sigmasq <- 1 / tau
s <- 1
smallest <- ranked(ypred[], s)       #  smallest predicted value
smallthan <- step(y[6] - smallest)   #   1 if smallest
              # predicted value is smaller than smallest obs value
}

data
list(y = c(28, 26, 33, 24, 34, -44, 27, 16, 40, -2, 29, 22, 24, 21, 25,
30, 23, 29, 31, 19, 24, 20, 36, 32, 36, 28, 25, 21, 28, 29,37, 25, 28,
26, 30, 32, 36, 26, 30, 22, 36, 23,27, 27, 28, 27, 31, 27, 26, 33, 26,
32, 32, 24, 39, 28, 24, 25, 32, 25, 29, 27, 28, 29, 16, 28), N=66)

inits
list(mu=20, tau=1 )