Chapter 6 Univariate models

In this chapter, we describe how to perform Bayesian inference in several of the most common univariate models, including the normal, logit, probit, multinomial probit and logit, ordered probit, negative binomial, tobit, quantile regression, and Bayesian bootstrap models for linear regression. Our point of departure is a random sample of cross-sectional units. We then present the posterior distributions of the parameters and illustrate their use through selected applications.

In addition, we demonstrate how to perform inference in these models using three levels of programming engagement: through our graphical user interface (GUI), via R packages, and by directly programming the posterior distributions. The first requires no programming skills, the second requires an intermediate level, and the third demands advanced skills. We also provide mathematical and computational exercises.

We can run our GUI typingshiny::runGitHub("besmarter/BSTApp", launch.browser=T) in the R console or any R code editor and execute it. However, users should see Chapter 5 for details.