This course is a review of econometric models and techniques and is intended to lead into the panel time series course subsequently taught in this series by Prof. Ron P. Smith.
The course surveys linear and nonlinear econometric models and
estimation techniques, presenting them in a method of moments framework. While emphasizing their applicability under general assumptions on the data generating process, the emphasis will be on applications in time series analysis.
The first part of the course treats single equation models, while the second part is devoted to systems of equations. Starting from a review of the linear regression model (OLS, GLS, FGLS), the course revisits basic properties of stochastic processes and their implications for time-series regressions, cast in the form of general autoregressive distributed lag (ARDL) and error correction model (ECM) representations. The course then takes an excursion to general nonlinear estimation based on sets of moment conditions (MOM, GMM).
The second part of the course is devoted to estimation of systems of equations that describe the joint evolution of several time series. After a brief review of seemingly unrelated regression (SURE) models, the primary focus is on vector autoregressive models (VARs). The concept of cointegration of time series is introduced, and its implications for VARSs is explored in the context of the vector error correction model (VECM) representation of VARs, as a multivariate generalization of ECMs for AR(DL)s.
The course is designed as a two-day sequence of alternating lectures and practical computer exercises. To the extent possible, the applications in the computer practicals will use time series data from microeconomic contexts, rather than macroeconomic series.