The work of the world's leading nutrition researchers appears to be riddled with statistical errors


#1

Originally published at: http://boingboing.net/2017/04/24/food-fight-3.html


#2

“X-ray vision carrots”

If I was a child I want to slap the guy/gal that made that up. Assuming lack of intelligence is not how you teach children.


#3

To be clear, there’s nothing wrong with p-hacking if you look at a big data set, find some intriguing correlations, and then perform a new study based on those hypotheses that you generated.

The cardinal sin is just using the original dataset to “prove” the correlations you found.


#4

This is why I love nutrients and hate nutritionists. I have seen too many parents with preposterous notes sent home from school because a kid had a balanced meal and a teacher thought otherwise. The schools are now overcompensating (read “covering their tracks”) for the $hit they introduced 25 years ago - junk food vending machines to bring in $$.

Also, what led to all of this were 4 “pizza papers.” If only there were a way to name this scandal to remind people of one of the most corrupt scandals in US history. Alas, that name is taken.


#5

Papasan for superintendent!


#6

Considering that nutritionists have been worshipping at the altar of Ancel Keys for the last 40 or 50 years, I can’t say I’m surprised.

Here’s my hypothesis: nutritionists (with a helping hand from the American Heart Association) are responsible for the obesity epidemic in America. By vilifying fat, Americans by and large have increased their reliance on sugar and carbs to make up the calorie deficit. Any endocrinologist can tell you what happens next.


#7

My favorite nutrition related video:
Dr. Peter Attia: The limits of scientific evidence and the ethics of dietary guidelines — 60 years of ambiguity


#8

Andrew Gelman has been blogging about this for a while now. One of the odd things about this is how strangely chill Wansink has been about the whole thing.

Wansink’s easygoing reactions seem to me to be dissociated from the seriousness of the problems that people have found with his work. A bunch of commenters on his blog have pointed out the obvious problems with his research methods, but he has just responded blandly in an in-one-ear-and-out-the-other kind of way.

Here’s a representative example. Anthony St. John writes:

With field studies, hypotheses usually don’t “come out” on the first data run. But instead of dropping the study, a person contributes more to science by figuring out when the hypo worked and when it didn’t.” [quoting Wansink]

I suggest you read this xkcd comic carefully: https://xkcd.com/882/

It provides a great example of learning from a “deep dive”. [quoting Wansink]

Brian Wansink replies:

Hi Anthony,

I like it. Thanks for the link. (Makes me grateful I’m more of a purple jelly bean guy).

Best,

Brian

Anyone who looks at that famous xkcd jelly-bean cartoon will immediately realize that it’s slamming the “deep dive and look for statistical significance” approach to research. But Wansink follows the link and . . . doesn’t get the point? Doesn’t realize that St. John, like most of the other commenters on the blog are saying he’s doing everything exactly wrong?

Also, the guy is a business school professor and apparently into behavior. I don’t think that he’s actually a nutritionist, just interested in human behavior relating to food.


#9

What makes you think I not?


#10

Maybe the best example ever of how “settled science” - isn’t.


#11

By golly, that Mr. Wansink seems to have certainly muddled things up quite a lot, if I understand the explanations correctly.

But I must say he is the SINGLE MOST EXCEEDINGLY POLITE MELONFARMER I have every seen on the internet.


#12

[quote=“Papasan, post:2, topic:99691”]
“X-ray vision carrots”

If I was a child I want to slap the guy/gal that made that up.
[/quote]The really weird thing here is that they’ve invented a stupid lie, and layered it on top of another, famous lie: the widespread claim that eating carrots gives you superior vision. Carrots are nutritious and delicious, but that particular notion is silly WWII-era propaganda that the Brits disseminated in the hopes it would be believed by the Germans to explain the success of British night-fighters against the Luftwaffe in the skies over England, which was actually the result of still highly classified radar technology. The Germans apparently weren’t fooled by the story, but a lot of other people have been.


#13

Then there’s research that gets it wrong at the very start:

http://www.npr.org/sections/health-shots/2017/04/10/522775456/drugs-that-work-in-mice-often-fail-when-tried-in-people


#14

so all of the nutrition stuff I have seen on FB is suspect now? I am shocked!!!

http://imgur.com/TWwXvMN


#15

A lot of nutritionists still cling to bad data from the 19th Century, like the “Spinach is high in Iron” myth (debunked early on but still widely believed almost 150 years later in part due to old Popeye cartoons).


#16

@knappa has already linked this above, but I’m one-boxing it here because it’s so relevant.


#17

Hah! I knew that all along ever since I saw this documentary from the future.


#18

Cory, would you put a hyphen in “leaf piles,” as in “leaf-piles”? No. So why “data-sets”?


#19

Nit-pickers.


#20

This topic was automatically closed after 5 days. New replies are no longer allowed.