I'm having some questions and hope some one could help me with them. When I plot the data into a boxplot, there is no top whisker but lots of outliers which is above the upper bound. enter image description here

As I'm looking for the answers, some materials explain how to interpret a boxplot without bottom whisker, but what about the top whisker? Could anybody hep me with this problem? Thank you,

  • 2
    $\begingroup$ I'm sure you'll have no problem looking up the definition of boxplot elements, but since most of these values are <30K while a few are >5M, you'd probably want to log-transform. $\endgroup$ – rolando2 May 9 at 12:44
  • 2
    $\begingroup$ Both whiskers are always present (provided the boxplot is correctly constructed--you can't trust all software to do that). You just don't see the top whisker at the left (for the EU) because it coincides with the top of the box. If you do have authorities that interpret an invisible bottom whisker, then just apply what they say to the negative of your values, because that switches the roles of the two whiskers. $\endgroup$ – whuber May 9 at 17:10

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.