Peter Diggle

My research concerns the development and application of statistical methods relevant to the biomedical and health sciences. In addition to my substantive post in the Lancaster Medical School, I hold a part-time post at the University of Liverpool Department of Epidemiology and Population Health and adjunct appointments at the Johns Hopkins University School of Public Health, Columbia University International Research Institute for Climate and Society, and Yale University School of Public Health. I am a trustee for the Biometrika Trust, a member of the Advisory Board for the journal Biostatistics, chair of the Medical Research Council’s Strategic Skills Fellowship Panel and President-Elect of the Royal Statistical Society.

Current Research

Spatial statistical methods are traditionally classified under three headings: continuous spatial variation; discrete spatial variation; spatial point processes. My current research in this area is aimed at developing a single methodology that can accommodate all three of these settings and enable principled statistical inference for multiple, spatially or spatio-temporally referenced, data-streams irrespective of data-format.

My current research on methods for analysing longitudinal data has two main themes: developing more flexible model-classes for the joint analysis of repeated measurement and time-to-event outcomes; models and methods for real-time analysis of observational data with long-term follow-up.

Both spatial and longitudinal statistical models provide methodological underpinning for the North of England HeRC (Health e-Research Centre), an MRC-funded Manchesterr-led consortium of four universities (Manchester, Lancaster, Liverpool, York) whose remit is to improve public health by developing and applying methods for the more effective exploitation of routinely recorded electronic health records. Current HeRC projects include: early detection of incipient renal failure in primary care patients; forecasting emergency emissions in a large children’s hospital; mapping geographical variation in NHS prescribing rates; real-time surveillance of gastro-enteric infections.

I am working on several public health projects in low-resource settings, where statistical modelling of spatial and temporal variation in disease risk can partly offset the lack of comprehensive registry data. Examples include: leptospirosis in an urban slum setting in northern Brazil; malaria risk mapping in Malawi; meningitis epidemic forecasting in the meningitis belt of sub-Saharan Africa.