What is it about?
There are many robust methods that improve on classic methods for comparing groups and studying associations. A practical issue for the non-statistician is understanding the relative merits of the many techniques that are now available.
Why is it important?
Robust methods can substantially improve power and provide a deeper, more nuanced understanding of data. Moreover, the choice of method can have a tremendous impact on how data are interpreted. The paper discusses these issues and provide a guide regarding when and how robust methods might be used.
The following have contributed to this page: Dr Rand Wilcox