统计建模博士职位

Vrije Universiteit Amsterdam is offering a fully funded, four-year PhD-position in statistics on survival analysis and extreme value theory, as part of the NWO-funded project “Seeing beyond the study duration: extreme value theory for long term survival and cure chances”.

This project will develop statistical methods and theory for analysing time-to-event data when a fraction of the population is immune to the event of interest (‘cured’). For example, in oncology the event of interest is cancer relapse/death, and the cured patients after treatment will never experience the event. However, in absence of a lifetime follow-up, cured patients cannot be distinguished from the uncured ones who do not show signs of the disease. A major constraint of most existing methods for cure models is the sufficient follow-up assumption, i.e. the study duration should be longer than the time span of possible events, which is rarely satisfied in practice. In this project, we will develop methods that relax this assumption by making use of extreme value theory (EVT) to extrapolate beyond the study duration. EVT has been well established for tail modeling and statistical inference on rare events that lie outside the range of the available data. We foresee applications of the developed methodology in several fields, but within this project we will focus on applications in oncology and credit scoring (for default prediction).

As a PhD candidate, you will join a collaborative team of two PhD candidates and two senior researchers, Dr. Juan Cai (VU Amsterdam) and Dr. Eni Musta (University of Amsterdam), who will also be your supervisors. Your research will center on developing cutting-edge estimation approaches for the cure rate and the survival time of the uncured depending on covariates (risk/prognostic factors, treatments). Your work will focus on developing statistical learning approaches that allow for high dimensional covariates and a non-linear dependence response, supported by theoretical guarantees on the accuracy of the method.

The project is expected to start in February 2027 , although the exact start date is negotiable.

Your duty As a PhD candidate you will: • conduct research within the specified project which involves development of statistical methodology and theory, implementation of the new methods in R, conducting simulation studies and real data applications • disseminate your research findings through publications in academic journals and presentations in international conferences • participate in relevant seminars and engage in research collaborations locally and/or internationally • participate in the School of Business and Economics PhD training program • complete and defend a PhD thesis within the appointment duration of four years • contribute to the department’s educational programmes (0.2 FTE) by teaching tutorials and supervising undergraduate students