Related Experiment Video
Updated: Nov 9, 2025

Optimization of Processing of Tiebangchui with Highland Barley Wine Based on the Box-Behnken Design Combined with the Entropy Method
Published on: May 19, 2023
Win odds: An adaptation of the win ratio to include ties
Edgar Brunner1, Marc Vandemeulebroecke2, Tobias Mütze3
1Department of Medical Statistics, University Medical Center Göttingen, Göttingen, Germany.
The proposed win odds measure, accounting for ties, is superior to the win ratio for comparing treatment benefits. This statistical approach offers improved inference in clinical trials.
Area of Science:
- Biostatistics
- Clinical Trial Methodology
- Statistical Inference
Background:
- The win ratio is a recent metric for comparing treatment group benefits.
- It handles data ties but ignores ties during statistical inference, posing challenges.
Purpose of the Study:
- To highlight the difficulties arising from the win ratio's handling of ties.
- To propose and evaluate the win odds as a superior alternative that incorporates ties.
Main Methods:
- Development of hypothesis tests and confidence intervals for the win odds.
- Evaluation of the win odds' properties using simulations.
- Application in a real-world case study.
Main Results:
- The win ratio's inference can be problematic due to ignored ties.
- The win odds effectively incorporate ties into the statistical comparison.
- Simulations and case study demonstrate the robustness of win odds.
Conclusions:
- The win odds provide a more reliable and comprehensive method for comparing treatment benefits than the win ratio.
- Statistical inference for clinical trials should prioritize methods that account for all data aspects, including ties.
More Related Videos
Related Concept Videos
Odds Ratio
Wilcoxon Signed-Ranks Test for Matched Pairs
Kendall's Coefficient of Concordance
Testing a Claim about Population Proportion
There are two methods of testing a claim about a population proportion: (1) Using the sample proportion from the data where a binomial distribution is approximated to the normal distribution and (2) Using the binomial probabilities calculated from the data.
The first method uses normal distribution as an approximation to the binomial distribution. The requirements are as follows: sample size is large...
Weighted Mean
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
Comparing Experimental Results: Student's t-Test

