Are you passionate about developing novel spatial-temporal statistical models and see the impact of your research? And are you eager to work with professionals from other scientific disciplines to implement your research? Do you aim to grow into an independent researcher that works at the edge between methodological innovation and application? Then you could be the next PhD student at our statistical data science impact group TRI-DSA [Teaching & Research Institute for Data Science Analytics] at the department of Mathematics and Computer Science (M&CS) of the Eindhoven University of Technology (TU/e).
Job Description The department of Mathematics and Computer Science (M&CS) of the Eindhoven University of Technology (TU/e) started recently a statistical data science research and impact group under the name of Teaching and Research Institute for Data Science Analytics (TRI-DSA:
https://tri-dsa.win.tue.nl/) The goal of TRI-DSA is to deliver trustworthy and state-of-the-art data science analytics to society through contract research, research support, professional courses & workshops, and development of (user-friendly) software and codes. Researchers working at TRI-DSA collaborate with professionals and researchers from internal and external organizations and companies on challenging data science problems. The current focus of TRI-DSA is on data science analytics for health and life sciences and in the data science research area of spatial and temporal data among others. TRI-DSA has several interesting ongoing collaborations (with e.g., pharma, hospitals, registries, eMTIC, ICMS, data science start-ups) and is in need of PhD student to support the research activities of TRI-DSA.
The PhD candidate should be interested in
- Developing and improving statistical data science techniques for real health and life science applications in the area of spatial-temporal data.
- Collaborating with non-data science professionals.
- Acting as research consultant for specific requests of the partners of TRI-DSA.
- Supporting the professional education and life-long learning activities of TRI-DSA.
The research focuses on developing generic spatial-temporal Poisson models (STPM's) that can adequately describe time-dynamic event rates across geographic areas and incorporate individual or aggregated geographic information. The main directions within the research will be developing spatial-temporal covariance structures, numerical (Bayesian and/or Frequentist) estimation methods, approaches for incomplete and missing information, and causal frameworks. An important element of the research will be the validation of the novel or improved data science analytics and the creation of easy-to-use algorithms and software. The intended PhD thesis will thus consists of both theoretical and applied work. The PhD candidate will be supervised and working with the researchers and collaborators of TRI-DSA.
An important aspect of the research is that it is being implemented (or at least ready for implementation) at external organizations and companies that are or will be working with TRI-DSA. TRI-DSA is currently working with medical spatial-temporal data from inhabitants of rural counties of the South of the USA, covid-19 data from different clinics in the Netherlands, and traveling disease survey data across the world.