Reading clickbait
Q: Did you see women who own horses live 15 longer than those who don’t?
A: Fifteen what? [thanks, David Hood]
Q: Years.
A: There’s an obvious reasons why women who own horses would live longer than those who don’t. Horses are expensive; women who can afford them will be more affluent than average. There could easily be other confounding factors, too
Q: But 15 years?!
A: Ok, that’s a lot. But remember, this is just an observational study — and it might not even be a representative sample. It could be some sort of clicky bogus poll
Q: Where they ask people if they own a horse and how old they were when they died? Yeah right.
A: Um. Ok. Maybe not a bogus poll. But 15 years just isn’t plausible, and it’s obviously not a randomised trial.
Q: “The double blind study followed women in different age groups over a forty year time frame to capture this objective data.”
A: Double blind?
Q: What it says.
A: How could you possibly have a double blind study of horse ownership?
Q: They could get alpacas instead. Or virtual reality games about horses. Or something.
A: That’s not double blind. That’s active-control. Double blind would mean you got an alpaca instead of a horse AND YOU COULDN’T TELL! Is there a link to the research?
Q: I hoped you’d find it, like you usually do.
A:
Q:
A: Really?
Q:
A: Ok. One of the other copies of this story says the lead scientist is Gary Cockburn. There are three papers on the PubMed database with a “G Cockburn” as author. None is even slightly related to this story. There are seven papers with a “Cockburn” as author and some reference to “horse”. None is even slightly related to this story. AND YOU CAN’T HAVE A DOUBLE BLIND STUDY OF HORSES!
Q: They made it up?
A: This is why you shouldn’t follow those links at the bottom of the page
Thomas Lumley (@tslumley) is Professor of Biostatistics at the University of Auckland. His research interests include semiparametric models, survey sampling, statistical computing, foundations of statistics, and whatever methodological problems his medical collaborators come up with. He also blogs at Biased and Inefficient See all posts by Thomas Lumley »
Q: What does this web site say about itself if you do scroll to the bottom of the page?
A: “This website is an entertainment website, jokes are created by users. These are humourous jokes, fantasy, fictional, that should not be seriously taken or as a source of information.”
6 years ago
Here some pages where the story appeared without that disclaimer, including some with more detail.
Perhaps the original source actually didn’t intended anyone to believe it, rather than just wanting a disclaimer. The other ones look as if they did want their readers to believe it.
6 years ago
It seems more likely that the last of those links is the original source (because they have more detail).
6 years ago
It does look like the one with more detail might be closer to the original. That one still doesn’t pass the sniff test, but at least it doesn’t add “double blind”. The way the story rapidly mutates and spreads across sites reminds me of p99-100 in Adam Rutherford’s 2016 book A Brief History of Everyone Who Ever Lived. The bogus headline was GINGERS FACE EXTINCTION DUE TO CLIMATE CHANGE, SCIENTISTS WARN. Rutherford’s observation: “Alas, a fiction can fly around the world before the truth has managed to pick the sleep from its eyes in the morning”.
6 years ago
Brilliant, Thomas! Best laugh I’ve had all week! I may write a song about this. Working title: “A double-blind study of horse ownership?!”
6 years ago
I’m sure I’ve read recommendations against generic terms like “double blind” because there are multiple roles that can be blinded. Five by these authors’ count:
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2947122/
So perhaps the double blinding in this case was outcomes adjudicators and data analysts.
I mean, obviously the “made up study” explanation does a more adequate job of explaining all the rest of the nonsense. But we should still do away with terms that count how many roles were blinded, in favour of detailing which ones were.
6 years ago
Yes, more detailed terms are absolutely better. And, separately, there’s a good case for terms such as “masked.”
I would still argue that using “double blind” for a study where participants knew what intervention they were getting would be close to the line between misleading and dishonest — and probably close on the wrong side of the line.
6 years ago
Yes — sorry my tongue was a little in cheek about stretching which two parties might be blinded (or, yes, masked) in “double blind”.
Though once you start thinking about interventions that comprise sentient beings, that adds another player into the mix that might have been blinded (or at least blinkered — I’m sure IRBs would have something to say about the animal ethics of actual blinding…).
Or maybe, given such a large effect size, it was the intervention designer who was blinded. They didn’t know whether they were designing a horse-ownership intervention… or a unicorn ownership one. As dad to two small unicorn-fan children, I have a feeling that unicorn magic could be sufficient to explain 15 extra years of life, and implausibly glossy hair for those 15 years to boot.
But to say any more would, I fear, be flogging a dead h…
6 years ago
Of course you can have a double-blind study; it just requires applying sufficient LSD to all survey participants.
Some get horses, some get flying alpacas, and those named Jacky get a magic dragon called Puff!
Now, about that ethics board application…
6 years ago