________________________________

From: [email protected]
[mailto:[email protected]] On Behalf Of 

>I just did an anaysis of IP traffic in Norway. It turns out that the
top 1% of users use 80%
> of the capacity and that 40% of the people use none at all. This is
almost perfect inequality. 

And also looks like the usual 'long tail' distribution. You could try
calculating the gini coefficient for this (looks close to 1!) and use
that as a way to analyse bandwidth usage inequality. Once you rank your
countries you can then ask questions about why different countries rank
as they do. Of course with sufficiently large sample sizes you can also
calculate the gini for different groups of people within (and across?)
countries.

>If you lie with the stats by taking the mean value, then it looks like
all of us are using
> a moderatly large amount of IP traffic when in reality it is just the
greedy guys who are
> eating the whole cake. 

Presumably usage-based charging resolves this? But that would then
preclude heavy usage by the least well-off? 

This analysis requires distribution statistics not just a mean. The
median would be an improvement...

Send me you data :-)

Ben

--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"mobile-society" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to 
[email protected]
For more options, visit this group at 
http://groups.google.com/group/mobile-society?hl=en
-~----------~----~----~----~------~----~------~--~---

Reply via email to