Hacker News Reader

This data is worthless and likely very skewed by the use of mean prices instead of the median, while not displaying the standard deviation.

Take France, for instance. 42 plans. 0.11 for the cheapest. 108 for the most expensive. How the hell are they finding 0.81 average, BTW? Same with South Korea.

Also, in my experience, the bigger the plan, the less expensive it is, so they should have sorted "per 1 GB/month plan" or controlled for that issue somehow.

View on HN

> How the hell are they finding 0.81 average

Probably by using median as you suggested? Because it's impossible for mean to be less than 2.68.

Which is not reality, if there were 1$, 100$ and 200$ you wouldn't say the avg person would pay 100.

Thats not what they said. If it was the average, the sum of all plans (42 @ 0.81) would be 34.02 which is less than the most expensive plan at 108.

Avg would be 100.3, but médian would be 100.

This is very obvious to me too. Australia is placing better than the UK, despite mobile contracts being almost universally more expensive and less good in Australia. It seems to be because there's an expensive UK plan skewing the data, despite not being what most people have.

Reply on news.ycombinator.com