ABSTRACT
When Cristoforo Colombo infamously sailed west in the year 1492, he believed that the Earth was spherical. In this, he was like most educated people of his day. Colombo made a prediction based upon his view that the world was small. But since he lived in a large world, aspects of the prediction were wrong. In his case, the error was lucky. The small world is the self-contained logical world of the model. Within the small world, all possibilities are nominated. Bayesian inference is really just counting and comparing of possibilities. This prior information could arise from knowledge of how the contents of the bag were generated. It could also arise from previous data. By working with probabilities instead of raw counts, Bayesian inference is made much easier, but it looks much harder. Bayesian data analysis usually means producing a story for how the data came to be.
