Damn statistics

[wmw999 2,584]

The "how many fatalities were there in 1989" comment got me to doing a little rec.skydiving research. I know there was a thread there about a significant drop in fatalities in the early 1980's (and there was).

So here goes:

Mike Johnston on 1980's overall fatalities (1991)
Statistical analysis of skydiving fatalities (1998) Unfortunately, the web page itself is gone, but the data may still exist (he's still at Ohio State)
Total number of fatalities per year 1963-1997 (nope, no breakdown by type of fatality).

With the overall small number of deaths, a little noise can make a difference. On the other hand, if we can start to look for type information over the years, maybe a body of knowledge can be developed, that eventually we can figure out something from.

Wendy W.

There is nothing more dangerous than breaking a basic safety rule and getting away with it. It removes fear of the consequences and builds false confidence. (tbrown)

[schattenjaeger 0]

Why are tandem fatality rates worse for the instructor?

[wmw999 2,584]

At the moment, this is just a collection. However, until sometime in the 90's AADs weren't required on tandems. Also, a TM is likely to try to save the student, and it might mean sacrificing him or herself. Tandem is way more complex than a regular skydive.

That, however, is just my opinion from listening. Not a lot of basis besides listening. Maybe if more data can come, there will be enough to draw some more knowledgeable conclusions.

Wendy W.

There is nothing more dangerous than breaking a basic safety rule and getting away with it. It removes fear of the consequences and builds false confidence. (tbrown)

[yoink 321]

if you want to do statistical analysis on fatalities within the sport, you need huge amounts of data about each jump ranging from age / experience of the jumper, to weather / adverse conditions and anything else you can think of... only this way can you try and say with any certainty "yes, doing X causes more fatalities than doing Y". Possible but very, very time consuming and as you say, the small sample size could lead to innacurate conclusions from misleading data.

[kallend 2,146]

Quote

if you want to do statistical analysis on fatalities within the sport, you need huge amounts of data about each jump ranging from age / experience of the jumper, to weather / adverse conditions and anything else you can think of... only this way can you try and say with any certainty "yes, doing X causes more fatalities than doing Y". .

This is also true of any epidemiological study, or for that matter, pretty much all research in the social sciences.

...

The only sure way to survive a canopy collision is not to have one.