Markov chain density plots
Whereas a trace plot captures a Markov chain's longitudinal behavior, a density plot illustrates the final distribution of the chain values. In turn, the density plot provides an approximation of the posterior model. You will construct and examine density plots of the \(m\) Markov chain below. The mcmc.list
object sleep_sim
and sleep_chains
data frame are in your workspace:
sleep_sim <- coda.samples(model = sleep_jags, variable.names = c("m", "s"), n.iter = 10000)
sleep_chains <- data.frame(sleep_sim[[1]], iter = 1:10000)
This exercise is part of the course
Bayesian Modeling with RJAGS
Exercise instructions
Apply
plot()
tosleep_sim
withtrace = FALSE
to construct density plots for the \(m\) and \(s\) chains.Apply
ggplot()
tosleep_chains
to re-construct a density plot of the \(m\) chain.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Use plot() to construct density plots of the m and s chains
# Use ggplot() to construct a density plot of the m chain
ggplot(___, aes(x = ___)) +
___()