An applied graduate introduction to time series methods for macroeconomics and finance. The course covers linear foundations (stationarity and ergodicity, ARMA models, the Wold representation theorem), Markov processes, vector autoregressions (VARs) and local projections (LPs), structural shock identification through using Cholesky, long-run, sign, narrative, and high-frequency identification, and linear and nonlinear state space models and estimation methods including the Kalman filter, particle filter, and sequential Monte Carlo. Bayesian inference and estimation methods are used throughout.

An undergraduate introduction to regression analysis, framed around the causal-inference toolkit now standard in applied economics. The course opens with a review of probability, statistics, and asymptotic theory (laws of large numbers, the central limit theorem), then develops ordinary least squares in the univariate and multivariate settings. The second half turns to the identification strategies used to recover causal effects from observational data — difference-in-differences, instrumental variables, and regression discontinuity — taught through applied examples in health, labor, and education economics.