If I have 50 people randomly split into 5 groups of 10 people, I can rank the groups based on their combined weight. If I were to rank each person based on their individual weight, what would be the most accurate way to recreate the original group rankings without knowing the actual weights of the individuals, just their rankings?

  • $\begingroup$ I really like the way Bagnall does it in the time-series-bakeoff. Each of the time-series gets a rank for how accurate for each of the tests, and then those ranks are combined into a "critical difference diagram". . The R library performanceEstimation has CDdiagram.BI and .Nemenyi. $\endgroup$ Mar 24, 2023 at 19:18


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.