model
{
	Tau.noninformative <- 1.0E-2
	P.gamma <- 1.0E-2
	for (i in 1:N.sample) {
		R.strep[i] ~ dpois(lamda[i])
		lamda[i] <- exp(log.lamda[i])
		log.lamda[i] ~ dnorm(mean.log.lamda[i], tau.noise)
		mean.log.lamda[i] <- (
			r[Id[i]] # individual effects
			+ beta[1] 
			+ beta[2] * Season[i] 
			+ beta[3] * Male[i]
			+ beta[4] * Age2[i]
			+ beta[5] * Age3[i]
			+ beta[6] * Age4[i]
			+ beta[7] * Age5[i]
		)
	}
	for (k in 1:N.beta) {
		beta[k] ~ dnorm(0, Tau.noninformative) # non-informative
	}
	for (j in 1:N.id) { # hierarchical prior
		# j = 1, 2, 3, .., 50
		r[j] ~ dnorm(0, tau.individual)
	}
	tau.individual ~ dgamma(P.gamma, P.gamma) # non-informative
	tau.noise ~ dgamma(P.gamma, P.gamma) #non-informative
}