Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

background

Clinical trials conducted in perinatal health often use measures of mortality, morbidity or a combination of both (composite) as the primary outcome measure evaluating the effectiveness of a particular intervention. When neurodevelopmental impairment is employed as the primary outcome measure in a trial (e.g. assessed by the Bayley Scales of Infant Development at 2 years of age corrected for prematurity), the presence of non-negligible mortality generates a problem of (informative) missing data in the primary outcome. To date, there is no consensus amongst methodologists regarding how to deal appropriately with this scenario because different imputation methods rely on assumptions that are often difficult to validate in the context of the study. For instance, the majority of imputation techniques available work well under the missing at random assumption of the missing data mechanism but not under the presence of informative ‘missingness’.  

The aim of this doctorate is to evaluate and assess different methods to impute missing primary outcome information in the presence of non-negligible mortality. Access to real trial data/information in perinatal health with varying degrees of missing data will be available and will inform a series of simulation studies to understand the implications of employing different strategies.

RESEARCH EXPERIENCE, RESEARCH METHODS AND TRAINING

During this project the student will be based in a large multidisciplinary research environment and will work closely with researchers and members of the Clinical Trials Unit at the NPEU. In addition, the student will also have access to researchers in other areas including epidemiologists, a psychologist, health economists and qualitative researchers. The student will learn advanced statistical methods to deal with missing data in clinical trials including maximum likelihood estimation, multiple imputation and inverse probability weighting. The Clinical Trials Unit at the NPEU has available a large archive and portfolio of high quality prospective trials conducted over the last decade, which will provide the source data to test the original hypothesis for this doctorate. This studentship will provide experience and training in literature review methods, specific courses on thesis management, training in advanced statistical modelling methods and programming techniques in statistical software such as Stata or R.

PROSPECTIVE CANDIDATE

This  project would suit a candidate with a strong quantitative (e.g. mathematics, statistics or epidemiology) background and/or a proven track record of previous experience in the analysis and interpretation of data from clinical trials, an interest in the issues surrounding missing data/outcomes ascertainment and the development of clinical trials methodology.

Supervisors