This is more of a methodology question than anything.

Scenario: you are trying to report average stats between two different groups responding to a variety of optional survey questions. But, (this is the annoying bit) somebody says "if the number of answers for a group on a specific question is too small (say, less than 2), the result for that question/group should be n/a".

So, Group A has 5 people respond with their ages. The average age is 65. Group B has only 1 person respond with an an age of 10.

According to the stipulation above, the results for average should be presented/reported as:

Group A: 65 Group B: n/a

Here is my question. Given the stipulation above, if you are then going to report on the average age of both groups, should the data from Group B be included?

Sorry if this is too basic a question, but it's bugging me. I keep changing sides.

  • $\begingroup$ I think you'll confuse people if you say "Group A average: 65, Group B average: n/a, Overall average: 55.8". This is technically an opinion question (you could do either one and just include a note on the report indicating which choice you made), but if you're going to include Group B in the average, some sort of footnote would be useful. $\endgroup$ – barrycarter Apr 21 '16 at 21:51
  • $\begingroup$ thanks, I was hoping there would be a rule of some sort as opposed to it being a matter of opinion... but if that's how it is, that's how it is. $\endgroup$ – Tbola Apr 22 '16 at 14:42

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.