PhD defence by Xiaoyi Wang

Title

Data Visualizations for Helping Users Understand Statistical Models

Abstract

Statistical models are playing a pivotal role in many domains (e.g., biology, chemistry, health care) and help users learn from data, find patterns, and make decisions. There is an increasing need for domain experts to use such models for understanding and solving domain-specific problems. However, domain experts may not be experts in data science. They may face two challenges when developing and using statistical models. One challenge is that the knowledge of non-expert users may be insufficient to evaluate statistical models in the model development process. The other challenge is that an insufficient understanding of statistical models may result in wrong decisions. To bridge the gaps between users’ comprehension and statistical models, this thesis investigates how interactive data visualizations help users understand statistical models.

Assessment Committee

Professor Katarzyna Wac, Department of Computer Science
Professor Heidrun Schumann, University of Rostock
Associate Professor Hans-Jörg Schultz, Aarhus University

Leader of defense: Irina Shklovski

Supervisors

Principal Supervisor Kasper Anders Søren Hornbæk

 For an electronic copy of the thesis, please contact phdadmin@di.ku.dk