Yuen's Trimmed-Mean Test (robust)
Coming soonT-Tests
This test is implemented and is currently going through StatMinds’ production verification: every statistic is independently checked against a trusted reference (scipy / R), locked with regression tests, and the screen is exercised across assumption-met/violated and significant/non-significant scenarios before it opens up.
See what’s live nowA robust two-group comparison of TRIMMED means — resistant to outliers and non-normality.
Yuen's test compares 20%-trimmed means using Winsorised variances, staying valid when outliers or skew would distort an ordinary t-test.
Worked example
Do two groups differ when outliers threaten the t-test?
Two groups with heavy-tailed data were compared with Yuen's 20%-trimmed t-test.
The trimmed means differed, Ty = 2.74, p = .009 — a difference the ordinary t-test missed due to outlier inflation.
Yuen's trimmed-means t-test showed a significant group difference, Ty = 2.74, p = .009.
When NOT to — use instead
- Clean, roughly normal dataThe ordinary two-group t-test is fine. → Independent-samples t-test
Ready to run a Yuen's Trimmed-Mean Test (robust) on your own data?
Guided setup, automatic assumption checks, effect sizes, figures and an APA write-up.
Run this test →