We see this frequent mistake people make when they analyze bottlenecks: They look at the average delays in the process. The problem with that is that some of the discovered process paths can be quite low-frequent. So, you run the risk of focusing on an area in the process that will not have a big impact when you improve it.
In this 3-minute video, we demonstrate how to alleviate this problem by combining the total duration with another metric, such as the mean duration, as a secondary metric in Disco.