On 1/6/04 10:22 pm, in article
[email hidden], "James Annan"
Quoted message said:No, the very basic error I was thinking of is the one they make in the
"60%" calculation. The ratio of the two numbers they calculate is
meaningless.
The drop in head injuries rate according to their stats is 3.6
percentage points. This is not a 3.6% drop in head injuries but a 13%
change (3.6/27.9)! However, the number of unhelmeted cyclists only
dropped by 5.8/84 = 7%. So according to their stats, the extra helmet
wearers did not only prevent their own head injuries but also stopped
injuries in a large number of those who were not wearing helmets!
I suppose you missed the point that the confounding factors are assumed to
apply to pedestrians as well and that pedestrian injuries typically act as a
good model for cyclist injuries. So comparing the change in cyclist HI with
the change in pedestrian HI, one presumes that the difference in change is
due to cyclists increased wearing of helmets.
Quoted message said:Since this conclusion is ludicrous, it is clear that there are huge
confounding factors which they did not take acccount of (some possible
ones are mentioned in the paper that references this one, which is
clearly linked).
The conclusion is ludicrous which is why they used pedestrian HI as a
control against which to benchmark the cyclist HI.
Quoted message said:
If that is not clear enough, consider a simple hypothetical: head
injury rates drop from 20% to 0% while helmet use increases from 0% to
100%. It is clear that helmet effficiency is 100% (all injuries are
prevented), and not 20/100=20% as Cook and Sheikh's method would
indicate.
No. You cannot take the extreme.
Assume cyclist HI drop from 50 to 25 percentage points. A 50% drop at the
same time that helmet use increases from 0 to 50 %.
What is the effectiveness of helmets if the mode of injury distribution
changes? how can we track this change? by using pedestrians. If over the
same time the HI rate in pedestrians stays at 50% then there is a
justification for claiming helmets have prevented all the injuries.
If pedestrian HI drop by 50% then one can claim that helmets have no effect
and that external factors are involved.
the figures to compare are Adult cyclists declined from a mean of 24.7 by
8.09 points (6.18-10.01). Adult pedestrians declined from 24.7 to 21. There
are no clear confidence intervals for adult pedestrians, just pedestrians as
a whole. Taking all cyclists and all pedestrians there is a significant
difference in rate of change (p=0.03).
So we have a change of one third for cyclists and one eighth for
pedestrians.
If pedestrians track cyclists we would expect to see a change to 21, not to
16.6 so we have a 4.4 point difference (or an increased saving of 4.4/21
points of head injuries.
This is nearly 25%.
The increase in helmet wearing is from 16 to 21.8 % so we see a decrease in
unhelemted cyclists from 84 to 78.2%, or 7%.
So we can calculate that 7% extra helmet wearing reduces head injury by 25%,
or each helmet prevents 350% of head injuries.
Quoted message said:Their calculation methodology would not be out of place on a P**l
S***h website.
It is much better than that but the answer is so obviously bogus that it is
hard to credit the study.
Quoted message said:I guess I get the prize...of writing to the journal and the authors to
explain their mistake.
Don't do it, you'll be laughed out of court unless you can come up with a
much better interpretation of the data than you already have. Mine would
need to be thoroughly worked over before letting anyone near it
professionally.
...d
