In modern economic research, computers enhance our capacity of analyzing complex problems with data support. Computation is particularly important in fields involving dynamic modeling, structural equations, and massive data, such as macro, labor, and industrial organization. However, computational methods have not been part of the core curriculum of postgraduate-level economics education, whereas programming skills are critical for a postgraduate’s success in academia and industry. The objective of this course is to introduce graduate students to commonly applied computational approaches for solving econometric models, with an emphasis on numerical optimization, Bayesian MCMC, simulation-based methods, and dynamic structural model estimation. We expect that at the end of the course a student would proficiently use at least one programming language (Stata, Matlab, R, etc.). Moreover, we aim to equip the students with the computational ability to tackle problems of their own research areas.