1. Multiple Tests.
- Author
-
Munko, Merle
- Subjects
- *
STATISTICAL hypothesis testing , *NULL hypothesis , *PROBLEM solving , *BONFERRONI correction - Abstract
The article "Multiple Tests" deals with hypothesis testing in statistics. It explains that in practice, there are often more than one hypothesis of interest, such as comparing means of multiple groups. It is pointed out that a test for the global null hypothesis, that all means are equal, can be conducted. If this null hypothesis is rejected, it can be concluded that there is a statistically significant difference between the means, but no precise conclusions can be drawn about which means differ. The article also addresses the issue of simultaneously testing multiple hypotheses and introduces the Bonferroni correction as a well-known method for solving this problem. However, it is noted that better methods can be developed if the dependency structure of the tests can be described in more detail. [Extracted from the article]
- Published
- 2024
- Full Text
- View/download PDF