AI Summary of Peer-Reviewed Research

This page presents an AI-generated summary of a published research paper. The original authors did not write or review this article. [See full disclosure ↓]

Publishing process signals: STRONG — reflects the venue and review process. — venue and review process.

Matched data pairs affect win ratio patterns and intervals

Engineering research
Photo by ThisIsEngineering on Pexels · Pexels License
Research area:EngineeringBiomedical EngineeringStatistical Methods in Clinical Trials

What the study found

The study found that as the number of matched data pairs increases, the win ratio statistic and its 95% confidence intervals change, but not consistently. The authors report that the confidence interval limits tend to move closer together, and that the count of win ratio values above one is not affected by the number of paired data.

Why the authors say this matters

The authors conclude that the number of paired data affects the number of significant win ratio results and the maximum win ratio. They also suggest that the win ratio confidence interval is influenced more by the data structure than by the size of the matched sample.

What the researchers tested

This was a simulation study on two composite endpoints, meaning endpoints that combine multiple outcomes into one measure. The researchers generated data for 35 scenarios with matched data pairs ranging from 10 to 1000, using the Python random library, and analyzed 34,101 data sets in total.

What worked and what didn't

The win ratio generally increased as the number of paired data increased, but the increase was not regular. The number of cases with a win ratio greater than one did not change with the number of paired data, while the number of win ratio values considered important increased. The lower and upper confidence limits moved closer together as paired data increased, though again not regularly, and the gap between them decreased.

What to keep in mind

The abstract does not describe limitations beyond the fact that the study is based on simulations. The findings are limited to the scenarios tested, which involved matched data pairs between 10 and 1000 and two composite endpoints.

Key points

  • The study used simulation data rather than real-world patient data.
  • Increasing matched data pairs changed the win ratio statistic, but not in a regular pattern.
  • The number of win ratio values greater than one was not affected by the number of paired data.
  • Confidence interval limits for the win ratio tended to move closer together as paired data increased.
  • The authors say the confidence interval is influenced more by data structure than by sample size.

Disclosure

Research title:
Matched data pairs affect win ratio patterns and intervals
Authors:
İsmet Doğan
Institutions:
Afyonkarahisar Sağlık Bilimleri Üniversitesi, Sağlık Bilimleri Üniversitesi
Publication date:
2026-04-25
OpenAlex record:
View
Image credit:
Photo by ThisIsEngineering on Pexels · Pexels License
AI provenance: AI provenance information is not available for this post.