The PyEcon project aims to make a humble contribution to promoting the use of the Python programming language in the field of econometrics and to fostering a proficient style of programming in economics. Over the past decade, the role of quantitative methods has become even more important in the social sciences. A variety of different proprietary and (meanwhile) free tools are used, such as, for instance, MATLAB, R or Stata.

The dynamic programming language Python is very well suited for use in economics and, in particular, in econometrics, where typically matrix-based calculations are involved. The scientific packages for numerical programming (NumPy), data preparation (pandas) and symbolic programming (Sympy) with many other well-known extensions provide an ideal framework for working scientifically in the field of economics.

We want to show why working with Python is fun. We want to bring economists and other interested individuals together to discuss how to write better code. We would like students to be able to understand the partly abstract theory of econometric methods employing practical examples and to achieve an enhanced understanding. Ultimately, we would be delighted to see a further improvement in the quality and reproducibility of scholarly work and studies.


We offer a course that introduces you to numerical programming with Python. The lecture is aimed at all people with interest in quantitative research but is primarily designed for an audience at the economics faculties. The course was planned, developed and implemented in the years 2017-2019 by Fabian Raters at the University of Goettingen with the support of Eike Manßen. We hold the lecture for the first time at the University of Goettingen in 2018. From 2020 onwards, we have started to extend the contents with learning material for modeling time series with MulTi project (JMulTi/MulTiPy), a multivariate time series meta package.

The stable version of the course materials, you find on this website, are open-access and may be shared with other students. For any further use, especially for teaching programming, please contact us.

If you have any ideas on how to improve or expand these materials or to improve the quality of this project, we look forward to your comments.


Data science




Fabian H. C. Raters

Eike Manßen