Hi, I have a bean plot as attached. Need help in interpretation.
What do the longer horizontal white lines inside the shape represent (e.g. the longer line next to count 10), compared to series of smaller white lines of same length. What is the significance of these longer lines?
How to identify the outliers?
Thanks,
Mainak.
These white lines seem to indicate individual values. If there are two identical values, the line is drawn twice as long, if there are 3 identical values, the line is three times as long. So that's actually a simple histogram with the resolution of the variable.
"outliers" are outlying points, points beeing very far wawy from the "bulk" of values. There is not much more about the definition of an outlier. Hence, those values that are far away from the bulge of the gray area would be considered "outliers". Such values I would expect (given this figure) to be larger than 30 or smaller than 2. For such values I would start becoming sceptical if I could trust them. However, please keep in mind that there won't be a reason to remove such "outliers" from the analysis as long as you don't have any external reason to classify them as "invalid".
Thanks so much Jochen Wilhelm, it was an clear and insightful explanation.
- Badges
- Science topic
- Similar topics
- Psychology