Data analysis is the basis of any evidence-based managerial decision-making. Data analysis is about recognizing patterns in data so that inferences about the real world can be made. The course teaches students about causal inference using selected methods of data creation, collection, and analysis. It draws on econometrics and statistical methods developed to estimate economic relationships, testing theoretical hypotheses and evaluating policies.

In particular, this course will provide a review of regression analysis including linear regression with multiple regressors, non-linear regression models and dummy variables. In addition the course will cover the methods of laboratory and field experiments, specific approaches to establish causal relations with observational data, such as Differences-in-Differences Regression and Regression Discontinuities. (We may also cover Instrumental Variables if there is time.) In addition, we will cover how to apply all these concepts in the statistical software R.

On successful completion of the course, you should:

• understand the concept of evidence-based decision-making;
• be able to choose the right method of statistical data analysis to answer a research question;
• have a good understanding of the discussed methods as well as their limitations;
• understand the difference between causality and correlation;
• be able to present and discuss findings from your research; 
• perform simple analysis using statistical software.

Full attendance is expected for all lectures. If you cannot attend a lecture due to exceptional/unforeseen circumstances, please contact the lecturer. If you show symptoms of COVID-19 or are affected by quarantine, do NOT participate in in-person lectures. Please contact your lecturer by email, and we will deal with the absence on a case by case basis. If mode of lectures is affected by a change in the COVID-19 situation, we will announce any changes in due course in class and by email.

The data course is centered on specific problem-based examples and case studies. Typically, we will start a topic with one or more examples and discuss how to find and/or collect data to answer these questions. This is followed by an introduction of the respective analysis method. In in-class tasks and homework assignments, students are asked to try out data analysis themselves, with data provided to them.

Participation in class and/or homework presentations (20%)

Homework assignments (30%)

There will be homework assigned in nearly all lectures. We will discuss homework in class.

Group project (50%)

Basic knowledge in statistics. The course will cover some basics in the first unit and then focus on more advanced statistics (data analysis, regressions, R,..)

ims@wu.ac.at