Research Associate / Senior Research Associate in Statistical Modelling

The role

Questions of test accuracy have recently been brought into the limelight by the COVID-19 pandemic: Which of several tests for a disease or condition is best? How accurate, and how cost-effective, is a testing strategy (e.g. Test A then Test B if Test A is positive, or repeated use of Test A)? How can we evaluate how accurate a test is when there is no gold standard to compare against? These are, in fact, important questions across all kinds of clinical areas. This post offers the opportunity to improve and develop statistical methodology to address these questions within a Bayesian evidence synthesis framework. You will work with Dr Hayley Jones on a new MRC/NIHR-funded project, to evaluate, extend and develop methods to synthesise networks of evidence on diagnostic test accuracy, widely applicable across clinical areas. This is an excellent opportunity for a statistician with an interest in Bayesian analysis to develop their skills and contribute to improving methodology in an important area.

You will be based at the Department of Population Health Sciences at Bristol Medical School, home to the NIHR Health Protection Research Unit in Behavioural Science and Evaluation (HPRU-BSE), the National Institute for Health and Care Excellence (NICE) Guidelines Technical Support Unit and, from April 2022, an NIHR Technology Assessment Review group. You will have the opportunity to work on several applied analyses of test accuracy relevant to NICE and/or the HPRU-BSE, and to disseminate methods developed through training courses and methodological support documents.

What will you be doing?

• Compare the properties of proposed methods for synthesis of comparative diagnostic test accuracy, and of latent class models for evaluation of test accuracy when there is no gold standard
• Evaluate these models
• Work with Dr Hayley Jones to develop new and/or extend existing statistical models for diagnostic test evaluation as required, in a Bayesian statistical framework
• Work on applied questions of comparative test accuracy of relevance to NICE and/or the HPRU-BSE
• Write papers for publication in high impact peer-reviewed journals
• Produce guidance documents and/or tutorial papers to facilitate use of methods in practice
• Contribute to production and delivery of short course training on evidence synthesis of test accuracy
• Build and maintain collaborations with other leading researchers in this field

You should apply if

• You would like to contribute to development of statistical methods to address important applied questions, applicable across clinical areas
• You have training or experience in Bayesian statistics, and some experience in using Bayesian software (e.g. WinBUGS / JAGS / Stan)
• You are highly numerate and hold a postgraduate degree in statistics, medical statistics or other relevant discipline
• You want the opportunity to further your training and enhance your skills, working as part of a leading research group in Bayesian evidence synthesis methodology
• You have excellent organisational skills and attention to detail
• You are a clear and concise communicator, both orally and in writing

For informal enquires please contact Hayley Jones, hayley.jones@bristol.ac.uk

We welcome applications from all members of our community and are particularly encouraging those from diverse groups, such as members of the LGBT+ and BAME communities, to join us.