Lecture, three hours; discussion, one hour. Limited to Master of Applied Statistics students. Overview of theory and practice of expectation maximization (EM) optimization methods, bootstrap, Monte Carlo simulation, and Markov chain Monte Carlo. Coverage of missing data, EM algorithm and its variants, nonparametric and parametric bootstrap, bootstrap inference, permutation tests, rejection sampling, importance sampling, Metropolis/Hastings algorithm, and Gibbs sampling, with brief introduction to Bayesian computing. Letter grading.