Course Syllabus
Econometrics Applied : Making Data Talk |
|
Semester & Location: |
Spring 2020 - DIS Copenhagen |
Type & Credits: |
Elective Course - 3 credits |
Major Disciplines: |
Economics |
Faculty Member: |
Holger Sandte |
Program Director: |
Susanne Goul Hovmand - sgh@dis.dk |
Program Coordinator: |
Alex Berlin- ab@dis.dk |
Program Assistant: | Marissa Buffo - mbu@dis.dk |
Time & Place: |
TBD |
Course Description
Data is the raw material of the information age, the new gold, as some say. Knowing how to handle and analyze data and to draw the right conclusions is a key qualification not only in a business environment, but for a wide range of professions. This qualification can only grow in importance.
This course is an introduction to a specific kind of data analysis - the science and art of building and using econometric models.
Applied econometrics is when theory meets data from the real world in order to answer a research question. It is the application of quantitative methods to explain the relationship (strength and direction) between variables or to forecast future trends. The techniques can be applied to a wide range of questions in economics and beyond, for example:
- What is driving sales of a good – the price or the marketing expenses?
- What determines wages - Education? Experience? Attractiveness?
- Do smaller classes improve learning?
- Does democracy increase economic growth?
- Does higher education reduce crime rates?
- On financial markets, models can be used to forecast stock prices
The beauty of econometrics is the chance to base the answers to this type of questions on theory and empirical methods instead of gut feeling, prejudice or anecdotal evidence.
The purpose of this course is to give students insight and experience in how to apply basic econometric methods to relevant topics. The course consists of lectures and a large number of smaller and larger exercises both in class and at home. The lectures will lay the necessary theoretical groundwork. Some of the practical exercises can be done in Excel, others with econometric software like STATA or EViews.
The first step will be to develop a feeling for data and data problems. Much of the course will be about regressions, i.e. explaining – in a statistical sense – a dependent variable by one or several independent variables, based on economic (or other) theory. While it is quite easy nowadays to make a computer print an econometric output, interpreting the results carefully is vital for good econometric practice.
The students will learn to build regression models, to interpret the results carefully, to judge the quality of the model and also what to do when the assumptions behind the model are not fulfilled. The students will also learn about causality tests and the basics of times series analysis and forecasting. To do this some statistical theory is necessary as a foundation for econometrics.
Key course themes
1) Introduction to Econometrics
Typical questions
Overview over methods
Do's and don'ts
2) Review of statistical concepts essential for econometrics
Data: sources (not least European sources), types, quality, pitfalls
Descriptive statistics and correlations
Handling data – frequency conversions, deseasonalizing etc.
Probability concepts
Hypothesis tests
Exploring statistical functions in MS-Excel
3) The classical linear regression model (Ordinary Least Squares, OLS)
What it’s all about
Making sense of the OLS method
Assumptions
Interpreting simple and multiple regression results
Assessing the statistical significance of regression results
Qualitative and dummy variables
Lagged variables
Exploring regression functions in MS Excel
Estimating regressions with an econometric software
Forecasting from a single equation (e.g. current and next quarter’s GDP)
Examples for a case study:
Explaining low inflation in the Euro area?
The ECB's reaction function
4) What to do when OLS assumptions are violated
Detecting and dealing with collinearity
Detecting and dealing with heteroskedasticity
Detecting and dealing with autocorrelation
5) An introduction to time series analysis
Stationary processes
Time series with a long memories: nonstationary processes
A drunk and her dog - cointegration
Example for a case study: Forecasting stock indices
The course is not about programming or Big Data. However, mastering basic econometric techniques on a smaller scale, naturally opens the door for handling large amounts of data.
Learning objectives
At the end of the course, the students should
- have a sense for the power and limitations of the econometric methods studied
- be capable the use MS-Excel’s statistical and regression functions
- be capable to work with the principles of the linear regression model
- be capable to use an econometric software to build their own regression models
- be capable to draw the defendable conclusions from large amounts of data
- be capable to do basic time series analysis
- have proven the capability to develop an econometric research project
- have learned to remain humble even when the model looks perfect
- have significantly increased their knowledge about Europe/Scandinavia as a by-product of having worked on European/Scandinavian questions and data
- have increased their cross-culture skills
- have increased their collaborative skills.
Faculty
Holger Sandte studied Economics and languages in Germany and France. MSc (Economics, University of Hanover) 1993, PhD 1998 (Dr. rer. pol, University of Trier) with a thesis on whether moderate inflation harms economic growth (answer: mostly not, but it depends). Econometric methods like regressions and VAR-models made up a large part of the empirical section of the thesis. Later on, during his many years as a bank economist, Holger used such methods as well as time series analysis to explain and forecast interest rates and exchange rates. Then he switched sides, dealing with government debt and financial market regulation at the Danish Ministry of Finance for a while. With DIS since 2019.
Holger firmly believes that
- finding answers to relevant real-world questions by combing theory with empirical work is a truly satisfying experience for students and ...
- ... that students acquire important skills if they learn how to handle data competently.
Readings
... will bring the students in contact with experienced users of econometric tools e.g. in think tanks or consulting firms.
Guest Lecturers ...
... will be invited to widen the students' perspective.
Approach to Teaching
A mix of lectures and exercises of varying complexity, do be done alone or in small groups.
Expectations of the Students
Prerequisites: One course each in macro- and microeconomics at university level. The students should be familiar with Excel and have basic knowledge in statistics – and no allergy to equations and working a lot with data.
Prior knowledge of econometric software would be helpful but is not required.
Active engagement/participation is important.
Evaluation
Engagement/participation in class: 20%
Various tests and exercises: 50%
Econometric research project: 30%
A Word about Grades
We realize that grades are important to you, but try not to let your anxiety about grades deter you from taking intellectual risks and learning just for the joy of learning. Also, we do not grade to punish or reward you just as our grade is not an indication of our evaluation of you as a person. We grade you to give you our honest assessment of your academic performance at this point in time.
Note: To be eligible for a passing grade in this class you must complete all of the assigned work.
Disability and Resource Statement
Any student who has a need for accommodation based on the impact of a disability should contact the Office of Academic Support (acadsupp@dis.dk) to coordinate this. In order to receive accommodations, students should inform the instructor of approved DIS accommodations within the first two weeks of classes.
Policies
Attendance
You are expected to attend all classes, guest lectures, workshops and field studies. If you must miss a class for religious holidays, medical reasons, or other valid reasons, you must let us know as far in advance as possible of the absence and obtain information about the work you must do to keep up in class. If you miss a class for any other reason (sudden illness, family emergency, etc.), you should get in touch with us as soon as possible and arrange to make up the work missed.
It is crucial for your learning that you stay on task and hand in assignments on or before the due date. All work– including in-class projects – have to be completed in order to pass the class. Late papers or projects will be marked down with 1/3 of a grade for each day it is late.
Academic Honesty
Plagiarism and Violating the Rules of an Assignment
DIS expects that students abide by the highest standards of intellectual honesty in all academic work. DIS assumes that all students do their own work and credit all work or thought taken from others. Academic dishonesty will result in a final course grade of “F” and can result in dismissal. The students’ home universities will be notified. DIS reserves the right to request that written student assignments be turned in electronic form for submission to plagiarism detection software. See the Academic Handbook for more information, or ask your instructor if you have questions.
Academic Regulations
Please make sure to read the Academic Regulations on the DIS website. There you will find regulations on:
DIS - Study Abroad in Scandinavia - www.DISabroad.org
Special note about laptop use in class: Use of laptop computers in class is allowed for the purpose of note-taking ONLY; other computer activities can prove distracting. Students May lose their laptop privileges if they use their computers for other activities besides taking notes. Students should also refrain from any activity/behavior that may be disturbing to other students who are making the effort to be attentive.
Course Summary:
Date | Details | Due |
---|---|---|