I'm not sure what the point of this article is, the author claims 3 deaths at Burning Man is not unexpected because the age-adjusted mean death rate in the US predicts that you'd expect 4.9 deaths. But at no point in the history of Burning Man has there ever been that many deaths, the article itself states that 3 deaths is the most at any Burning Man so far. So 4.9 deaths is not even close to actual average death rate expected for a "mean" Burning Man. And since the prediction of 4.9 deaths on average is wrong, any conclusion based upon that 4.9 deaths expectation is poorly founded. The author just seems to ignore that their model does not match the data at all. It's like if I used how many hot-dogs are in my fridge to model the Burning Man death rate, then at no point acknowledged that these two variables have no connection, either real or spurious, to each other. This is just mystifying to me.
it did go on to talk about the uncertainty, especially given the low numbers:
There is a 27% chance that we would observe 3 deaths or less, given an average rate of 4.9 deaths. This is also known as a p-value.5 6Why isn’t our p-value greater? Seems like 27% is quite low. By scientific standards, this isn’t abnormal at all. Observing 3 deaths is completely within reason.
However, the relative uncertainty of our point data is quite large at about 58% (1/sqrt(3)). This is the size of the error. If we were talking about death rates in the thousands, we might have an error of 3% or less. But the reality is that at such low counts, our data is considered quite “fuzzy”.
(I haven't been on over 10 years, but back in the early 2000s there were always rumours about deaths that the organisers managed to ensure ended up categorised as not happening at the event. People who died in ambulances on the way to hospital, or in hospital after injury at the event, or on the road in or out of the event...)
0PingWithJesus · · focus · HN ↗
bigiain · · focus · HN ↗
There is a 27% chance that we would observe 3 deaths or less, given an average rate of 4.9 deaths. This is also known as a p-value.5 6Why isn’t our p-value greater? Seems like 27% is quite low. By scientific standards, this isn’t abnormal at all. Observing 3 deaths is completely within reason.
However, the relative uncertainty of our point data is quite large at about 58% (1/sqrt(3)). This is the size of the error. If we were talking about death rates in the thousands, we might have an error of 3% or less. But the reality is that at such low counts, our data is considered quite “fuzzy”.
(I haven't been on over 10 years, but back in the early 2000s there were always rumours about deaths that the organisers managed to ensure ended up categorised as not happening at the event. People who died in ambulances on the way to hospital, or in hospital after injury at the event, or on the road in or out of the event...)