Introduction

Please note that this is a preliminary course description. The final version will be published in June 2026.

In the 21st century, information is created, digitized, and stored at unprecedented rates. The availability of high-dimensional, large-scale datasets has transformed the landscape of business analytics and data science, providing new avenues for insightful decision-making. However, vast datasets alone are insufficient for addressing fundamental analytical questions central to contemporary research and practice.

This course introduces the potential outcome framework as a rigorous foundation for causal inference. We explore microeconometric techniques designed to uncover causal relationships using experimental and quasi-experimental data. We discuss the promise and pitfalls of large-scale experimentation and consider empirical applications relevant for business and policy analysis.

Course content

The course covers the following topics:

  • The potential outcome framework
  • Large-scale experimentation
  • Noncompliance
  • Treatment effect heterogeneity
  • Regression discontinuity designs
  • Difference-in-differences and event studies
  • False positives, p-hacking and publication bias
  • Supplementary analysis and replication

Disclaimer

This is an excerpt from the complete course description for the course. If you are an active student at BI, you can find the complete course descriptions with information on eg. learning goals, learning process, curriculum and exam at portal.bi.no. We reserve the right to make changes to this description.