Multilevel modeling of single-subject experimental data
Handling data and design complexities.
Integrating digital tools in daily practice of healthcare.
Empirical data play a key role in the application domains studied by itec. These include a wide variety of quantitative and qualitative data and structured and unstructured data. Within statistical modeling, itec further develops, evaluates and applies complex statistical techniques for collecting, visualizing, and modeling quantitative data. Although the techniques in principle are often widely applicable across domains, this strand of research is feeded by questions and challenges within itec’s application domains, and in turn advances the applied research.
Handling data and design complexities.
Within machine learning and AI, we adapt existing and develop new machine learning algorithms to tackle open questions in the applications domains of itec. We mainly focus on non-standard supervised and semi-supervised learning tasks, such as multi-output prediction, time-to-event prediction and interaction prediction. We typically target three goals in our methods: predictive performance, efficiency and interpretability.
Data in various domains is two-dimensional: there are two data types and the values of interest