Whisker plots of parameter posterior distributions
Displays whisker plots for specified parameters on the same plot, with a point at the mean value for the posterior distribution and whiskers extending to the specified quantiles of the distribution.
whiskerplot(x, parameters, quantiles=c(0.025,0.975), zeroline=TRUE)
x |
A jagsUI object |
parameters |
A vector of names (as characters) of parameters to include in the plot. Parameter names must match parameters included in the model. Non-scalar parameters with multiple values (e.g. |
quantiles |
A vector with two values specifying the quantile values (lower and upper). |
zeroline |
If TRUE, a horizontal line at zero is drawn on the plot. |
Ken Kellner contact@kenkellner.com.
#Analyze Longley economic data in JAGS
#Number employed as a function of GNP
#See ?jags for a more detailed example
#Get data
data(longley)
gnp <- longley$GNP
employed <- longley$Employed
n <- length(employed)
data <- list(gnp=gnp,employed=employed,n=n)
#Identify filepath of model file
modfile <- tempfile()
writeLines("
model{
#Likelihood
for (i in 1:n){
employed[i] ~ dnorm(mu[i], tau)
mu[i] <- alpha + beta*gnp[i]
}
#Priors
alpha ~ dnorm(0, 0.00001)
beta ~ dnorm(0, 0.00001)
sigma ~ dunif(0,1000)
tau <- pow(sigma,-2)
}
", con=modfile)
#Set parameters to monitor
params <- c('alpha','beta','sigma','mu')
#Run analysis
out <- jags(data = data,
inits = NULL,
parameters.to.save = params,
model.file = modfile,
n.chains = 3,
n.adapt = 100,
n.iter = 1000,
n.burnin = 500,
n.thin = 2)
#Examine output summary
out
#Generate whisker plots
#Plot alpha
whiskerplot(out,parameters=c('alpha'))
#Plot all values of mu
whiskerplot(out,parameters='mu')
#Plot a subset of mu
whiskerplot(out,parameters='mu[c(1:3,7)]')
#Plot mu and alpha together
whiskerplot(out,parameters=c('mu','alpha'))Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.