A rigorous introduction to linear and nonlinear econometric methods. The course builds the asymptotic toolkit, studies linear regression and ordinary least squares, then turns to causal questions and treatment effects, from selection on observables and instrumental variables to the local average treatment effect. It closes with the theory of extremum estimation and the generalized method of moments.

The course covers the static linear panel model, from pooled OLS and random effects to the fixed-effects model, clustering, and time effects, then dynamic panels and modern difference-in-differences, the theory of extremum estimation, and nonlinear models for limited and qualitative dependent variables such as binary choice, censored and truncated regression, and sample selection.

An introduction to probability and statistical inference for economists. The discussion sections review probability and random variables, expectation and common distributions, sampling and estimation, hypothesis testing, and an introduction to linear regression. Each session works through exercises and exam-style problems to build intuition and problem-solving skills.

A Julia package to estimate Bayesian Vector Autoregressions with Minnesota, sum-of-coefficients, and dummy-initial-observation priors. It performs structural analysis through sign restrictions or external instruments, and provides tools for hyperparameter selection, posterior sampling, impulse-response and forecast-error-variance decompositions, historical decompositions, and both unconditional and conditional forecasts.

Solutions to the problem sets and final exam of ECON210C (Monetary Economics, Prof. Johannes Wieland, Spring 2024). The code implements modern solution methods for RBC and New Keynesian DSGE models, including the method of undetermined coefficients and the sequence-space approach of Auclert et al. (2021), together with identification strategies for structural VARs based on recursive ordering and the external instrument approach.