PhD Researcher for “Heterogeneity in Studies with Discrete-Time Survival Endpoints: Implications for Optimal Designs and Statistical Power Analysis”, Netherlands

This project is funded by a VIDI grant from the Netherlands’ Organization for Scientific Research (NWO). The PhD student will spend time on doing research, following mathematics and statistics courses of IOPS and other institutes, and spend about 10% of the time on teaching courses at the BSc level. The PhD student will be supervised by Dr M. Moerbeek.

The aim of trials on event occurrence is to study if and when a particular event, such as onset of daily smoking or entry into parenthood, occurs. The timing of events may be in thin and precise units or in coarser intervals. In the second case one does not know the exact timing of the event; one only knows that it occurred within a particular time interval. Such discrete-time survival data are typically analyzed on basis of a generalized linear model, such as a logistic regression model.

The main research question in any trial is whether an experimental treatment differs from a control with respect some outcome variable. As many covariates or background variables, such as age and socio-economic status, may have an effect on the outcome they should be measured and included in the statistical model. Ignoring such variables may result in biased estimates of the treatment effect estimator and hence incorrect conclusions with respect to the effect of treatment.

The aim of this project is to investigate to what extent such biases occur and how they can be corrected for in the statistical model. We will also focus on the optimal design of trials with covariates and discrete-time survival data. The PhD student will write papers in international scientific journals, contribute to international conferences and write a PhD thesis.

Qualifications: