We finalized some results using ANOVA Two Way and now facing difficulties to report the statistical significance in the figures. We do not know if we use the factor significance (Factor 1, Factor 2 and Interaction among them) or if we use the multiple comparisons test (Tukey's, Bonferroni, Sidak, etc.).
Looking at figures in literature we realize that there is no unanimity, so we would like some tips and suggestions.
Assuming a two-way ANOVA with factors A and B, each with two levels, once you have a significant interaction, you must preform a simple effects analysis. That is, test Factor A at B1 and again at B2. Then, test Factor B at A1 and at A2. At this point, the main effect tests become superfluous. In other words, the main effect tests have no meaning. Use the simple effects. They would explain the significance of the differences between each level in the interaction graphs. if there are more than two levels of each factor, you can use Tukey or other multiple comparison procedure to compute the simple effects and control the Type I error rates.
@ Marcel Rodrigues Ferreira ,
Kindly let me know whether your design is a factorial one. Have you allocated the 4 treatment combinations to the experimental plots?
Show me the ANOVA table with the numerical results.
Interpretation depends upon the numerical results in the ANOVA table.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Graphs