In recent years, the ability to analyze large amounts of data has called into doubt the need for scientific theories. A simple response to this is that predictive theories based on correlations in big data, are scientific theories too. A more substantial response is that, even though correlation is sufficient for prediction, it is not sufficient for the explanation of effects in terms of causes, mechanisms or reasons. Whenever we want to understand the phenomena we study, we should look for causes, mechanisms, or reasons, which means that we should build scientific theories. In this tutorial I provide a bird’s eye view on how to produce a clear and defensible theoretical contribution. I focus on design theories and start with a brief introduction of the role of theories in the design cycle. I will then review the structure of design theories, and identify the different kinds of steps that researchers follow to reason from data to theories: descriptive, statistical, abductive and analogic inference. In conclusion I will explain how these inferences must be related to research goals and research setup. The tutorial will be illustrated by examples from information systems, software engineering and other engineering disciplines.

When and where

Wednesday 13th, 11h — 12:30h (Sala d’Actes, Vertex)

Speaker’s bio

Roel Wieringa occupies the chair of Information Systems at the Department of Computer Science at the University of Twente, The Netherlands. His research interests include requirements engineering, enterprise architecture, and design scien ce research methodology for information systems and software engineering. He has written three books, Requirements Engineering: Frameworks for Understanding (Wiley, 1996), Design Methods for Reactive Systems: Yourdon, Statemate and the UML (Morgan Kaufmann, 2003), and Design Science Methodology for Information Systems and Software Engineering (Springer, 2014).