I am working on plant breeding and need to compare many genotypes in the breeding process. What is the best post-hoc test to compare differences between 10, 20 or 30 genotypes?
Each of these is used traditionally in agricultural research.
I would take the advice of Jochen Wilhelm here: https://www.researchgate.net/post/When_to_use_tukey_and_duncan_multiple_comparison_test_Which_is_best_Do_they_give_same_results
Thank you very much for your interest and recommendation. Sal Mangiafico
The most appropriate multiple comparison test in filed experiments is Tukey test, because in such as conditions the experimental design could be with factorial arrangement. For this reason, it is important to take into account the experimental design of the experiment and the experimental conditions in which that research is carried out. Duncan's test is only valid for one-factor experiments, while Tukey's test can be used in experiments with a factorial arrangement and of course has greater power according to Fonseca-Pantoja, unpublished, 1990.
Thank you very much for your interest and answer. Angel De Souza-Torres
Volkan Mehmet Cinar in addition to what is recommended, I suggest that you consider the number of treatments that you have designated in your research, since based on these the means comparison tests are selected, in this way and as an example, it can be said that the mean comparison test Duncan's analysis is only robust or reliable when three treatments are used; beyond this number the error increases, incurring type I or II error.
Best regards
Thank you very much for your interest and answer. José Leonardo Ledea Rodríguez
- Badges
- Science topic
- Similar topics
- Philosophy
- Esthetics
- Interpretation