Hi
Could you please help me
I am trying to fit a Multilevel Poisson regression with the following code
## BUGS CODE
## Multilevel Poisson regression
model {
for (i in 1:n){
y[i] ~ dpois (lambda[i])
log(lambda[i]) <- mu +
b.species[Species[i]] + b.quarter[Quarter[i]] + epsilon[i]
epsilon[i] ~ dnorm (0, tau.epsilon)
}
mu ~ dnorm (0, .0001)
mu.adj <- mu + mean(b.species[]) + mean(b.quarter[])
tau.epsilon <- pow(sigma.epsilon, -2)
sigma.epsilon ~ dunif (0, 100)
for (j in 1:n.species){
b.species[j] ~ dnorm (0, tau.species)
b.species.adj[j] <- b.species[j] - mean( b.species[])
}
tau.species <- pow(sigma.species, -2)
sigma.species ~ dunif (0, 100)
for (j in 1:n.quarters){
b.quarter[j] ~ dnorm (0, tau.quarter)
b.quarter.adj[j] <- b.quarter[j] - mean(b.quarter[])
}
tau.quarter <- pow(sigma.quarter, -2)
sigma.quarter ~ dunif (0, 100)
}
##
skate.data <- list ("Species", "n.species", "Quarter", "n.quarters", "y")
#radon.inits <- function (){
# list (a=rnorm(J), b=rnorm(1), g.0=rnorm(1), g.1=rnorm(1),
# sigma.y=runif(1), sigma.a=runif(1))
#}
skate.parameters <- c ("mu", "b.quarter", "b.species", "sigma.species",
"sigma.quarter", "sigma.epsilon")
skate.3 <- bugs (skate.data, inits=NULL, skate.parameters, "skates.bug",
n.chains=3, n.iter=500,
bugs.directory="c:/ProgramFiles(x86)/OpenBUGS/OpenBUGS323",
program=c("OpenBUGS"))
But I always receive this message error
Loading required package: BRugs
Welcome to BRugs connected to OpenBUGS version 3.2.3
model is syntactically correct
Error in aperm.default(datalist[[i]]) :
invalid first argument, must be an array
In addition: Warning messages:
1: package 'BRugs' was built under R version 3.0.3
2: In FUN(X[[5L]], ...) : class of 'x' was discarded
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
