# MSB104 Econometrics

## Course description for academic year 2023/2024

### Contents and structure

MSB104 Econometrics is the compulsory master’s level course in econometrics. It builds on the bachelor’s course in statistics, and prepares the student for further studies in advanced econometrics. This course provides the student with a broad knowledge about statistical methods for analysing single equation, multi variate, econometric models on, as well as a deep understanding for the ordinary least squares regression model and its properties. The methods are applied on primarily cross-section and time-series data, but the students are also introduced to panel data.

In addition to the theoretical approach, the students learn how to apply statistical software to carry out their own analysis, using the free cross-platform package "R".

Finally, the students will learn how to draw valid inference using sound statistical thinking.

### Learning Outcome

Learning outcomes

Knowledge

· a deep knowledge of fundamental least squares regression analysis applied in economics and its properties.

· a strong critical awareness of potential mis-interpretations of of the outcomes of empirical analysis (e.g. causation vs. correlation), as well as a good understanding of the basic challenges related to the various methods and datastructures.

· a good knowledge of the elementary procedures for model validation.Problems related to heteroscedasticity, autocorrelation, model specification, multicollinarity and non-stationarity.

· Theoretical background for the standard methods used in empirical analyses for statistical testing of hypothesis.

Skills

· Carry out a basic empirical analysis on a given dataset, formulate basic econometric models, estimate parameteres, make predictions, test relevant hypotheses, and how to draw sound inference from the results

· basic use of the statistical package "R" for econometric analyses.

· perform statistical tests to investigate whether the classical assumptions in regression analysis are satisfied.

· be a critical reader of other empirical analyses.

Competance

· be able to read and understand project reports and journal articles that make use of fundamental statistical concepts and methods

· be able to make use of econometric models in your own academic work, for example in analyses needed for your master’s thesis

· Develop a cricitical attitude to statistical analysis

None

### Recommended previous knowledge

A basic course in statistic analysis and scientific method is strongly recommended. It is also strongly recommended that you passed the Data Science course or take part in it in the same semester.

### Teaching methods

Lectures, data-workshops and assignments.

### Compulsory learning activities

Learning portfolio.

The students will build a portfolio based on the written assignments that are given during the course. The assigned tasks must be evaluated as approved (godkjent) to be eligible for the submission of the portfolio at the end of the semester.

### Assessment

Portfolio.

The students will build a portfolio based on the written assignments that are given during the course. The portfolio will be assessed on a scale A-F.

The tasks must be written in English.

### Examination support material

All available aids allowed. The students shall adhere to normal scientific citation practice, and portfolio documents will be checked for plagiarism.