Visualization tools of statistical post-hoc test results
| Acronym: | PostHoc |
| Project type: | Consulting RTD |
| Time frame: | 2003 |
| Funding agency: | UGent |
| Geographic keyword: Europe | Belgium | |
| General keyword: Software development | |
| Specific keyword: Visualisation tools | Large multidimensional data sets |
Visualisation tools for Post-hoc tests associated with Non-parameteric Multiple-way Analysis of Variance
Multiple-way Analysis of Variance is used when purpose is: looking for difference in the medians of conditions (treatments). Consequently, with a multiple-way ANOVA following hypothesis is tested:
H0 median condition 1 = median condition 2 = ... = median condition N
H1 median condition 1 != ... != median condition N
However, if the ANOVA results in the acceptance of H0, some groups still might have significantly different group means. To pinpoint these groups, post-hoc tests are necessary. Within the framework of this project, a multiple comparison algorithm (the case of all pair wise comparisons with Dunn/Bonferroni type adjustment) and associated visualization tools were elaborated. The figures below show a 2D grid of all possible pair wise comparisons and the calculated post-hoc test value.
Legend to the figures:
Figure 1:
Figure 2:

funding agency