A Robust Procedure for Comparing Multiple Means under Heteroscedasticity in Unbalanced Designs
Esther Herberich, Johannes Sikorski, Torsten Hothorn · 2010
Read A Robust Procedure for Comparing Multiple Means under Heteroscedasticity in Unbalanced Designs by Esther Herberich, Johannes Sikorski, Torsten Hothorn (2010) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0009788.txt.
Description
Comparing averages across groups is a basic task in almost every science. Esther Herberich, Johannes Sikorski, and Torsten Hothorn proposed a stronger way to do it. Their procedure appeared in PLOS ONE in 2010. Real data rarely fit the tidy assumptions of textbook tests.
The method handles heteroscedasticity, where groups spread out by different amounts. It also handles unbalanced designs, where groups hold unequal numbers of cases. Both problems can mislead standard tests and distort conclusions. A robust procedure gives researchers fairer comparisons when data are messy. The procedure was built for everyday research data.
Catalog record
| CREATOR | Esther Herberich, Johannes Sikorski, Torsten Hothorn |
|---|---|
| YEAR | 2010 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| LICENSE | Creative Commons Attribution License |
| RIGHTS | CC BY |
| SOURCE | PLOS ONE |
Source: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0009788