Applied Statistics

With an increasing demand for the provision and explanation of meaningful statistics to navigate through the data-driven modern world, our research focuses on the development and application of statistical models to real-life problems in the fields of health, medicine and social science.

Statistics are ubiquitous in everyday life with an increasing demand on both the provision and explanation of meaningful statistics to navigate through the data-driven modern world. Our research focuses on the development and application of statistical models to real-life problems emanating from, amongst others, the fields of health, medical and social science.

The strengths of our group lie in the ability to handle complex data occurring over both time (such as longitudinal, time series and time-to-event data) and space (for instance, data collected over a set of geographical areas) as well as data varying jointly over both space and time. Bayesian methods are often used in the modelling of such data and there is also expertise in handling missing data.

Examples of current and recent research include disease mapping, survival analysis and predictive modelling in contexts such as addressing health inequalities in both developed and developing countries along with evaluation of crime prevention strategies.

Current areas of expertise are:

• Joint models for longitudinal and time-to-event data
• Bayesian modelling of spatial and spatial-temporal data
• Missing data, distribution theory, data mining and risk predictions
• Statistical methods applied to epidemiology
• Survival analysis and evidence synthesis (meta-analysis)
• Health economics and health technology assessment, medical imaging, infectious diseases modelling and global health (including environmental health)