Work package 7: Statistical Analysis
Leader: Prof. Philip Bath, University of Nottingham
Design the Statistical Analysis Plan and then perform the final statistical analyses of all outcomes of interest.
This can be split into the following component objectives:
- Develop a statistical analysis plan
- Develop analysis software
- Check the central database
- Perform the final statistical analysis
The statistical work will be done at the Nottingham Stroke Trial Unit (NSTU).
Description of the tasks
Appropriate use of statistical methodology and analysis is essential for evaluating the benefits and harms of the PRECIOUS study interventions, and for providing reliable interpretation of the results.
The primary outcome of interest in PRECIOUS is the score on the so-called ‘modified Rankin Scale’, which is a scale for measuring the degree of disability or dependence in daily activities of patients who have had a stroke. Other outcomes of interest are the quality of life and the extent of cognitive functioning after stroke. The team at the Nottingham Stroke Trial Unit will perform several statistical analyses to assess whether any of the three medical treatment in PRECIOUS improves functional outcome on the ‘modified Rankin Scale’, quality of life and cognitive functioning at three months in patients with acute stroke, compared to patients who did not receive any medical treatment in PRECIOUS.
In addition, in subgroup analyses, the team will assess whether one or more particular patient groups are more or less likely to benefit from each of the interventions, based on for example age, sex or stroke severity. In collaboration with the UMCU, the technical description of the statistical methodology and procedures for performing the statistical analysis will be written down in the Statistical Analysis Plan, which will be completed before the end of the study. Additionally, statistical software will be developed by the Nottingham Stroke Trial Unit to analyse the data which is collected during the PRECIOUS trial.
Once the information of the last patient in PRECIOUS has been collected at the end of the study, the final statistical analysis will be performed according to the Statistical Analysis Plan. Also, the team at the Nottingham Stroke Trial Unit will use the data of PRECIOUS to develop prediction models, which could be used in clinical practice to predict the occurrence of infections or poor outcome in elderly patients with acute stroke.