Multiple Comparisons

The Multiple Comparisons plot type helps to analyze precisely whether or not each pair of sounds within the dataset received significantly different ratings, thanks to rigorously-applied statistical analyses (namely multiple comparisons using the Bonferroni correction).

This type of analysis is based on the error bar graph, and was created for two goals:

• Evaluate, according to the ratings, whether the average rating of a sound is significantly different from that of another sound: Significant Differences.

• Define groups or classes of sounds' average ratings that are not significantly different from each other, to get a discretized ranking of the sounds ("Class A", Class B" etc.): Segmented Ranking.