报告题目：Understanding and Modeling Subjective Expectations

报告人：Prof. Tobias Rossmann, Technical University of Applied Sciences Augsburg, Germany

报告时间：2026年5月7日上午9:30-11:00

报告地点：信息学馆307

邀请人：电气工程系罗艳红教授

报告内容概要：

The first presentation explores the statistical modeling of subjective expectations within household survey data to better understand real-world decision-making. Following a general introduction to subjective expectations across various domains, the focus shifts to the reported stock market expectations of Dutch households between 2004 and 2016. Utilizing a statistical panel data model, this talk analyzes and estimates heterogeneity, biases, reporting types, and updating behavior. The presentation concludes by discussing the quantification of uncertainty at several levels.

报告人简介：

Prof. Tobias C. Rossmann received his Ph.D. degree in Econometrics from LMU Munich, Germany, in 2019. During his doctoral studies, he also conducted a research visit at the University of Southern California, Los Angeles, United States, in 2018. He received his M.Sc. degree in Economics with a specialization in Econometrics and Statistics from LMU Munich in 2015, after completing an Erasmus exchange year at the University of Warwick, United Kingdom. He also received his B.Sc. degree in Economics from LMU Munich in 2013. From 2019 to 2020, he worked as a Data Scientist at the Advanced Analytics Lab of UniCredit in Munich, Germany. From 2020 to 2023, he served as a Data Scientist in Predictive Analytics at Versicherungskammer Bayern, Munich. Since 2023, he has also worked as a freelance Data Scientist and AI Consultant. In 2023, he joined the Technical University of Applied Sciences Augsburg, Germany, where he is currently Full Professor of Statistics and Machine Learning in the Faculty of Liberal Arts and Sciences. Since 2024, he has served as a member of the Examination Board for the B.Sc. Data Science program, and since 2025, he has been the International Program Coordinator of the B.Sc. Data Science program. His research interests include econometrics, statistics, panel data, dynamic finite mixture models, subjective expectations, causal machine learning, explainable artificial intelligence, generative music, and applied data science. His teaching covers quantitative methods, data analytics, machine learning, statistical modelling, mathematics, and statistics.