What is it about?
An n-of-1 trial one in which different treatments are tested on different episodes on the same subject. Where a number of such subjects have been tested together, using such an n-of-1 trial, then the datasets created present various challenges of analysis. Following some brief comments on design of such trials, various possible questions that might be addressed are described and linked to various possible analyses. There is a close relationship to conventional analysis and this makes use of software to analyses such trials possible. A minor change in data-preparation is required and this is described, explained and justified.
Featured Image
Photo by National Cancer Institute on Unsplash
Why is it important?
This work is unique in that it carefully links analyses to different questions, thus resolving previous confusion about which analyses are appropriate by showing that it is the choice of question to be answered that makes the difference.
Perspectives
I had been arguing for many years in various places that a powerful approach for personalising treatment in the context of chronic relatively stable disease was to run series of n-of-1 trials. I finally decided that it was necessary to write a thorough but as simple as possible explanation as to how one might do this.
Professor Stephen J Senn
Consultant Statistician
Read the Original
This page is a summary of: The analysis of continuous data from n-of-1 trials using paired cycles: a simple tutorial, Trials, February 2024, Springer Science + Business Media,
DOI: 10.1186/s13063-024-07964-7.
You can read the full text:
Resources
Contributors
The following have contributed to this page
