|Funding for:||UK Students, EU Students|
|Funding amount:||£14,777 per annum|
|Placed On:||8th October 2018|
|Closes:||23rd November 2018|
This project is one of a number that are in competition for funding from the ‘GW4 BioMed MRC Doctoral Training Partnership’ which is offering up to 18 studentships for entry in September/October 2019.
The analysis and interpretation of randomised trials should in principle be straightforward: we compare the outcomes in those patients randomised to the novel treatment to the outcomes in those randomised to the control treatment. In practice things are more complicated. Patients may die before the outcome of interest can be measured. They may stop taking their randomised treatment or start taking other treatments.
What has traditionally been called the intention to treat effect estimates the effect of randomisation. Depending on the setting and stakeholder, this ‘estimand’ may not correspond to the scientific question of interest, particularly when for example treatment compliance in the trial is not reflective of what would be seen in routine clinical practice or patients switch to other treatments during follow-up. Alternative estimands include those that estimate the effect if treatment compliance had been maintained somehow, or the effect in a sub-population who would have fully complied under randomisation to either treatment. Depending on the setting, there may be material differences in the magnitude, and potentially even direction, of different estimand effects, such that clear pre-specification of a trial’s estimand(s) is critical.
The proposed project will involve exploration and development of statistical methods for estimating different types of estimand, in the context of the recently published ICH E9 draft addendum on estimands. This will likely involve a combination of exploiting existing methods developed in the causal inference and missing data literature together with development of new methods. It will likely involve a mixture of theoretical arguments based on statistical theory and simulation studies. In addition, real clinical trial datasets will be analysed to illustrate the methodological developments. Depending on the interests of the student, it may also involve development of accompanying statistical software to facilitate uptake of the methods by clinical trialists. The papers and software generated during the proposed project would be expected to have immediate and tangible impacts on the design and analyses of both publicly funded and industry clinical trials. After the PhD the student will be extremely well placed to take their next career step in either academic research or industry.
IMPORTANT: You should apply using the DTP’s online application form: https://cardiff.onlinesurveys.ac.uk/gw4-biomed-mrc-dtp-student-2019
For more information on the application process visit:
You do NOT need to apply to the University of Bath at this stage – only those applicants who are successful in obtaining an offer of funding from the DTP will be required to submit an application to study at Bath.
Studentships cover Home tuition fees, Training Support Fee and stipend (£14,777 p/a, 2018/9 rate) and are open to UK/EU applicants who have been resident in the UK since September 2016.
Type / Role: