Take the 2-minute tour ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

Following my question at SD to calculate Burstiness, I realised that it Standard Deviation is not very effective to represent burstiness. Does anyone have an idea how do I calculate burstiness more accurately?

The definition of burstiness here is that, if A set contain 3 numbers {2000,2000,2000} and B contain 3 numbers {0, 500, 0}, B is more "bursty" than A, and ideally burstiness(A) should be 0

share|improve this question
    
Why is the standard deviation insufficient here? sd(A) = 0 and sd(B) > sd(A), so it satisfies your conditions. –  01000100 Jan 8 '12 at 12:26
    
Probably the example I gave wasn't too good, the actual data is about 14 days, so the actual burstiness among group wasn't really significant –  cherhan Jan 8 '12 at 12:32
    
this paper proposes a burst intensity index: "The Effects of Query Bursts on Web Search" –  user46484 Oct 29 '12 at 22:59

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.