@Rickyfox doesn't they describe it in section 3.1 ?

@Tim they use a and c throughout that section but I don't see how these have anything to do with the step in the algorithm

@whuber Is my reading of the subtext correct? That the study design is fatally flawed because it's testing an irrelevant comparison -- planes with 0m altitude are not the use-case for parachutes? And also that this is a flaw with how medical testing is carried out: a person with a disease would not volunteer to be placed on a placebo medication? I'm not familiar with how medical trials are conducted, so I'm not sure what the target of this satire is outside of the obviously pointless experiment

or is it just that randomized controlled trials are only good if the "laboratory setting" is ignorable - in this case, the "lab setting" is entirely divorced from reality?

certainly this will become a classic of the genre along the same lines as the paper about a dead salmon in the fMRI

Another entry in the fine tradition of BMJ's silly Christmastime articles.

I think the point best demonstrated is the issue of floor effects. If you have a 0% injury rate, you can't see any beneficial effect from an intervention to reduce injury rate.

> PArticipation in RAndomized trials Compromised by widely Held beliefs aboUt lack of Treatment Equipoise (PARACHUTE) trial