3.0

credits

Average Course Rating

The main goal of this course is to provide the students the alternative viewpoint of the Bayesian approach vis-à-vis the classical econometric approach based on the frequentist perspective. The course will present the basic principles of Bayesian inference, Bayesian Analysis of the linear regression model and extensions of the regression model, and the numerical methods used for Bayesian implementation. Modern Bayesian econometrics relies heavily on numerical simulation methods and computational algorithms. With the advancement of computing power and the advent of new simulation methods, simulation based Bayesian methods have become increasingly popular in practice with a large and growing number of applications. A significant part of the course will be devoted to explaining and demonstrating how numerical Bayesian methods, particularly, Markov Chain Monte Carlo (MCMC) methods, such as the Gibbs sampling and the Metropolis-Hastings algorithm, can be applied to estimate various interesting models in economics and finance. Students will develop practical experience with posterior simulation through hands on computer exercises involving computer programming. Prerequisites: 440.606 Econometrics.