Statistical Analysis of Choice Behaviour

If one wants to design effective (transport) systems, one needs to understand the behavior of -future- users of these systems, e.g. the market share of a new public transport service. If one wants to design effective (transport) policies, one needs to know how people will respond to these policies, e.g. impact of a tax incentive on electric vehicle sales. This course sets out to provide students with in-depth knowledge and hands-on experience with behavioral theories, mathematical models, and statistical methods, and data collection methods that have proved very effective in understanding and predicting human choice behavior.

Importantly, this course takes a quantitative (i.e., mathematical and statistical) perspective on choice behavior; this is quite different from the usual perspective in behavioral science courses, which tends to be more qualitative. More specifically, we formalize behavioral theories into mathematical models, which we then estimate on empirical datasets using cutting-edge statistical methods. In combination, the estimated econometric 'choice models' support rigorous analysis and forecasts of quantitative phenomena, thereby playing a crucial role in private and public sector policy development.

The theories, models, and methods that are taught in this course are applicable -and have been used- throughout a wide variety of domains, including but not limited to Transportation, Health, Marketing, Environment and Energy, and Political sciences. As such, our course optimally prepares students for a wide range of (quantitative, empirical) topics for their graduation projects.

The course will cover both canonical (and Nobel Prize-winning) methods, which are grounded in theories of choice behavior, as well as more recently proposed methods which are based on machine learning.