This course serves as an introduction to contemporary econometric techniques. It places an emphasis on both theory and applications, and the connection between the the two. We develop the theoretical tools necessary to construct estimators that are useful for standard economic problems, and prove that these estimators have (or do not have) desirable properties such as efficiency, consistency, and unbiasedness. In seeing how these estimators are built, you will learn common econometric techniques that you may use to build your own customized estimators; you will also become familiar with the concepts that are used in the applied econometrics literature, enabling you to read sophisticated empirical papers. This course begins with a review of probability theory and statistical inference, and places it in the matrix-based notation that we will use for the rest of the course. We then introduce the linear regression model and its large-sample and small-sample properties, and discuss ways in which data often violate the assumptions of the model and how to deal with these violations. By the end of the semester, you will have seen a thorough treatment of the general linear model, so that you will be ready to handle specific topics (time series data, simultaneous equations, limited dependent variables, etc.) next semester.