If one wants to find out the posterior of the model parameters, the sim( ) function of the arm package becomes handy. The following R script will simulate the posterior distribution of parameters and produce a set of histograms:
>posterior.bayes <- as.data.frame(coef(sim(fit.bayes)))
>attach(posterior.bayes)
>h1 <- ggplot(data = posterior.bayes,aes(x = X1)) + geom_histogram() + ggtitle("Histogram X1")
>h2 <- ggplot(data = posterior.bayes,aes(x = X2)) + geom_histogram() + ggtitle("Histogram X2")
>h3 <- ggplot(data = posterior.bayes,aes(x = X3)) + geom_histogram() + ggtitle("Histogram X3")
>h4 <- ggplot(data = posterior.bayes,aes(x = X4)) + geom_histogram() + ggtitle("Histogram X4")
>h5 <- ggplot(data = posterior.bayes,aes(x = X5)) + geom_histogram() + ggtitle("Histogram X5")
>h7 <- ggplot(data = posterior.bayes,aes(x = X7)) + geom_histogram() + ggtitle("Histogram X7")
>grid.arrange(h1,h2,h3,h4,h5,h7,nrow...
