This report demonstrates how a multiple-choice knapsack dynamic programming (DP) approach finds optimal budget allocations without enumerating massive Cartesian products that make expand.grid() blow up RAM.

In this post, you'll learn how to compute the posterior distribution of simple and complex models both mathematically and numerically. Before diving into the computations, we'll review essential statistical concepts to build a solid understanding of the posterior and Bayesian inference in general. We assume that readers are familiar with probability theory, calculus, set theory and the R programming language