Introduction

The courses examines time series methods for data analysis with an emphasis on macroeconomic applications. The aim of the class is to provide students with a basic formal introduction to modern time series techniques, hands-on experience in applying them to real-world macroeconomic data, and understanding of how to bring data to bear on policy-relevant macroeconomic theories.


Module 1: Fundamentals of Time Series

Module 1 begins with a quick review of random variables, and hypothesis testing. It then introduces the basic elements of univariate time-series analysis: covariance stationarity, white noise process, moving averages, and autoregressive processes.


Module 2: Estimating and Using Univariate Linear Time Series Models

Module 2 studies the estimation of linear time-series models and their use for inference and for prediction.


Module 3 studies the properties of non-stationary time series, and analyzes alternative measures of trends and cycles.


Module 4: Vector Autoregressions

Module 4 studies vector autoregressions (VARs), starting with reduced-form analysis, and introducing structural VARs via the equations ordering (Cholesky Decomposition) approach.


Module 5: Cointegration and Spurious Regressions

Module 5 studies nonstationarity in a multivariate setting, analyzing spurious regressions, and cointegration.