Target group 
Master’s Programme in Economics. Open to other students as well. 
Timing 
At least every other year in the third period 
Learning outcomes 
After the course, the student should
 Be familiar with the main approaches to modelling macroeconomic data
 Know the basic properties of the linear vector autoregressive (VAR) model
 Understand the concept of the identification of economic shocks in structural VAR models, and be able to conduct structural analysis by shortrun and longrun identification restrictions in the VAR model
 Be able to apply methods of classical and Bayesian statistical inference in reducedform and structural VAR models
 Be able to report empirical research results obtained using the methods covered

Completion methods 
The course consists of lectures (24 hours) and exercises either in separate sessions or integrated into the lectures. The lectures (and exercise sessions) are not mandatory. There is a written final exam, a number of internet quizzes based on the homework assignments, and an empirical term paper. The homework assignments consist of analytical and empirical exercises. The former familiarise the student with the theory and calculations typically required in the practical implementation of the methods, while the latter teach skills of undertaking an empirical research project, including data handling, programming and interpreting results. 
Prerequisites 
The course builds upon the contents of Econometrics 1 and 2 or Advanced Econometrics 1 and 2. Hence, familiarity with statistical inference and matrices is assumed; knowledge of time series econometrics is useful. 
Recommended optional studies 
Knowledge of R is useful because it is used throughout. However, the basics needed for the practical implementation of the methods can be acquired during the course. 
Contents 
The course provides an introduction to the methods of modern applied macroeconometrics. The different approaches currently employed in applied work are reviewed, including the basics of empirical dynamic stochastic general equilibrium (DSGE) models, but the main emphasis is on the vector autoregressive model and its application in economics. In particular, we concentrate on the identification of economic shocks by various methods and the use of the structural vector autoregressive framework in policy analysis. Both classical and Bayesian approaches to inference in reducedform and structural VAR models are covered. Applications to financial market data may also be discussed. The emphasis is on the practical application of the methods discussed in modelling macroeconomic data. 
Study materials and literature 
In addition to the lecture slides, the reference manuals of the R packages covered in the course as well as selected parts of the following textbooks can be useful:
 Bjørnland, H.C. & L.A. Thorsrud (2015). Applied Time Series for Macroeconomics. Gyldendal Norsk Forlag AS, 2nd edition (1st edition can be used as well)
 Favero, C.A. (2001). Applied Macroeconometrics. Oxford University Press
 Hamilton, J. (1994). Time Series Analysis. Princeton University Press
 Lütkepohl, H. (2005). New Introduction to Multiple Time Series Analysis. Springer
In addition, a number of journal articles assigned by the lecturer are included in the required literature. 
Activities and teaching methods in support of learning 
All material related to the course is delivered through the Moodle area of the course, which also contains a discussion forum where students can discuss issues related to the course with each other and the teacher. During the lectures, the students can post spontaneous comments and questions in the Presemo room for the course. The lectures involve a number of activating questions, also answered through Presemo. Homework assignments involve multiplechoice questions that the students answer through Moodle. 
Assessment practices and criteria 
The grade on a scale from 0 (fail) to 5 is the weighted average of the grades of the final exam (40%), the quizzes based on the homework assignments (30%), and the term paper (30%). Each of the three components is graded on a scale from 0 (fail) to 5, and each must be passed separately. 