RCTs are mostly useful for interventions which have a smallish effect: Too small to be smack-in-the-face-obvious. For these an RCT is unethical anyway.
-
-
Replying to @BenLiddicott @AlexGodofsky and
So we are talking interventions where either * the probability of obvious success in an individual case is small * the effect size is small enough that without large numbers it's not distinguishable from noise.
1 reply 0 retweets 1 like -
Replying to @BenLiddicott @AlexGodofsky and
So it's a feel-your-way-snake-cave strategy that works sometimes for particular snakes. But it is not a panacea for uncertainty, nor a universal system for generating knowledge.
1 reply 0 retweets 1 like -
Replying to @BenLiddicott @AlexGodofsky and
No, we don't need an RCT for parachutes. Crash test dummies are calibrated by engineers against... * human volunteers * Cadavers * Monkeys The full details of the monkeys' contribution will make you sad. Keyword: Helmets.
1 reply 0 retweets 1 like -
Replying to @BenLiddicott @AlexGodofsky and
Even with all that there was a lot of inference involved. There is a reason engineers incorporate a "margin of safety".
2 replies 0 retweets 0 likes -
Replying to @BenLiddicott @eigenrobot and
Some of these claims about RCTs are true (some I disagree with but I'm not really interested in arguing those points), but virtually none of them are *actually* supported by the BMJ satirical paper, which paper is chuckleworthy as a joke but fails as critique.
2 replies 0 retweets 2 likes -
Replying to @AlexGodofsky @eigenrobot and
There is no BMJ paper. It doesn't exist. They didn't do the literature survey. They are making a satirical point. When people "cite" the "BMJ paper" they are not "citing" a "paper", they are making a satirical point. It is not a citation.
2 replies 0 retweets 1 like -
Replying to @BenLiddicott @eigenrobot and
Yes they are citing it (in the ordinary sense, not the formal scientific sense) to develop an argument and they develop that argument incorrectly because of flaws in the paper and the understanding of it.
1 reply 0 retweets 1 like -
Replying to @AlexGodofsky @eigenrobot and
There is no paper. There CANNOT BE FLAWS in a paper that does NOT EXIST. The whole thing is a poignant - so poignant - satire. Wake up. There is no path to truth that can be reduced to an algorithm you can follow. In particular, RCTs are not it.
1 reply 0 retweets 0 likes -
Replying to @BenLiddicott @eigenrobot and
My god, man. "The paper" as in the PDF. I can't tell if you don't understand what I mean or what.
2 replies 0 retweets 1 like
pls untag me gents :)
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.