↓ Skip to main content

Improving the analysis of composite endpoints in rare disease trials

Overview of attention for article published in Orphanet Journal of Rare Diseases, May 2018
Altmetric Badge

About this Attention Score

  • In the top 25% of all research outputs scored by Altmetric
  • High Attention Score compared to outputs of the same age (84th percentile)

Mentioned by

1 news outlet
7 tweeters


10 Dimensions

Readers on

21 Mendeley
You are seeing a free-to-access but limited selection of the activity Altmetric has collected about this research output. Click here to find out more.
Improving the analysis of composite endpoints in rare disease trials
Published in
Orphanet Journal of Rare Diseases, May 2018
DOI 10.1186/s13023-018-0819-1
Pubmed ID

Martina McMenamin, Anna Berglind, James M. S. Wason


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. 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. 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. 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.

Twitter Demographics

The data shown below were collected from the profiles of 7 tweeters who shared this research output. Click here to find out more about how the information was compiled.

Mendeley readers

The data shown below were compiled from readership statistics for 21 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
Unknown 21 100%

Demographic breakdown

Readers by professional status Count As %
Researcher 6 29%
Other 4 19%
Professor 3 14%
Student > Ph. D. Student 2 10%
Student > Doctoral Student 1 5%
Other 2 10%
Unknown 3 14%
Readers by discipline Count As %
Medicine and Dentistry 8 38%
Mathematics 3 14%
Nursing and Health Professions 1 5%
Pharmacology, Toxicology and Pharmaceutical Science 1 5%
Social Sciences 1 5%
Other 1 5%
Unknown 6 29%

Attention Score in Context

This research output has an Altmetric Attention Score of 14. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 13 June 2018.
All research outputs
of 17,368,632 outputs
Outputs from Orphanet Journal of Rare Diseases
of 1,840 outputs
Outputs of similar age
of 288,071 outputs
Outputs of similar age from Orphanet Journal of Rare Diseases
of 1 outputs
Altmetric has tracked 17,368,632 research outputs across all sources so far. Compared to these this one has done particularly well and is in the 90th percentile: it's in the top 10% of all research outputs ever tracked by Altmetric.
So far Altmetric has tracked 1,840 research outputs from this source. They typically receive a little more attention than average, with a mean Attention Score of 7.5. This one has done particularly well, scoring higher than 90% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 288,071 tracked outputs that were published within six weeks on either side of this one in any source. This one has done well, scoring higher than 84% of its contemporaries.
We're also able to compare this research output to 1 others from the same source and published within six weeks on either side of this one. This one has scored higher than all of them