Improving the analysis of composite endpoints in rare disease trials
View / Open Files
Authors
McMenamin, M
Berglind, A
Wason, JMS
Publication Date
2018-05-22Journal Title
Orphanet Journal of Rare Diseases
ISSN
1750-1172
Publisher
Springer Nature
Volume
13
Issue
1
Language
eng
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
McMenamin, M., Berglind, A., & Wason, J. (2018). Improving the analysis of composite endpoints in rare disease trials. Orphanet Journal of Rare Diseases, 13 (1) https://doi.org/10.1186/s13023-018-0819-1
Abstract
Background: Composite endpoints are recommended in rare diseases to increase power and/or to sufficiently capture complexity. Often, they are in the form of responder indices which contain a mixture of continuous and binary components. Analyses of these outcomes typically treat them as binary, thus only using the dichotomisations of continuous components. The augmented binary method offers a more efficient alternative and is therefore especially useful for rare diseases. Previous work has indicated the method may have poorer statistical properties when the sample size is small. Here we investigate small sample properties and implement small sample corrections. Methods: We re-sample from a previous trial with sample sizes varying from 30 to 80. We apply the standard binary and augmented binary methods and determine the power, type I error rate, coverage and average confidence interval width for each of the estimators. We implement Firth's adjustment for the binary component models and a small sample variance correction for the generalized estimating equations, applying the small sample adjusted methods to each sub-sample as before for comparison. Results: For the log-odds treatment effect the power of the augmented binary method is 20-55% compared to 12-20% for the standard binary method. Both methods have approximately nominal type I error rates. The difference in response probabilities exhibit similar power but both unadjusted methods demonstrate type I error rates of 6-8%. The small sample corrected methods have approximately nominal type I error rates. On both scales, the reduction in average confidence interval width when using the adjusted augmented binary method is 17-18%. This is equivalent to requiring a 32% smaller sample size to achieve the same statistical power. Conclusions: The augmented binary method with small sample corrections provides a substantial improvement for rare disease trials using composite endpoints. We recommend the use of the method for the primary analysis in relevant rare disease trials. We emphasise that the method should be used alongside other efforts in improving the quality of evidence generated from rare disease trials rather than replace them.
Keywords
Responder analysis, Composite endpoints, Improving efficiency
Sponsorship
MRC (unknown)
Cancer Research UK (18113)
Identifiers
External DOI: https://doi.org/10.1186/s13023-018-0819-1
This record's URL: https://www.repository.cam.ac.uk/handle/1810/280705
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.
Recommended or similar items
The current recommendation prototype on the Apollo Repository will be turned off on 03 February 2023. Although the pilot has been fruitful for both parties, the service provider IKVA is focusing on horizon scanning products and so the recommender service can no longer be supported. We recognise the importance of recommender services in supporting research discovery and are evaluating offerings from other service providers. If you would like to offer feedback on this decision please contact us on: support@repository.cam.ac.uk
The following licence files are associated with this item: