METHODS FOR EMPIRICAL ANALYSIS IN MACROECONOMICS

COURSE OUTLINE

This is a preliminary course outline, more details (page references etc) will be made available prior to the course.

• Large recap: dependence, stationarity, time series regression, arima models, forecasting, estimation, frequency domain methods.
• Vector autoregressive models: estimation, Granger-causality, impulse responses, variance decompositions.
• Primer on identification: structural vector autoregressive models and local projections with short run, long run, sign, heteroskedasticity and external instruments based identification schemes.
• State space methods: local level example, filtering, smoothing, parameter estimation, missing values, forecasting.
• Primer on dynamic factor models: state space formulation, principal components, number of factors, nowcasting

MATERIAL & SOFTWARE

The syllabus contains a long list of topics. Each topic corresponds to roughly two or three lectures. Due to time constrains I might skip over some of points listed to be able to cover some of the more interesting and cutting edge topics.

The empirical examples that are covered during the course are made available to the students in R. However, the empirical assignments may be done in any preferred coding language, e.g. Python, Matlab, Ox, Gauss, etc