RJAGS로 배우는 Bayesian 모델링

The two-parameter Normal-Normal Bayesian model provides a simple foundation for Normal regression models. In this chapter, you will engineer the Normal-Normal and define, compile, and simulate this model using rjags. You will also explore the magic of the Markov chain mechanics behind rjags simulation.

In this chapter, you will extend the Normal-Normal model to a simple Bayesian regression model. Within this context, you will explore how to use rjags simulation output to conduct posterior inference. Specifically, you will construct posterior estimates of regression parameters using posterior means & credible intervals, you will test hypotheses using posterior probabilities, and you will construct posterior predictive distributions for new observations.

In this final chapter, you will generalize the simple Normal regression model for application in broader contexts. You will incorporate categorical predictors, engineer a multivariate regression model with two predictors, and finally extend this methodology to Poisson multivariate regression models for count variables.