Paul Alper points us to a news article that reports:
Oz research rejected from 2003 surgery conference, resulted in 2-year ban
In May 2003, Mehmet Oz was the senior author on a study that explored a hot topic at the time . . . But Oz was forced to withdraw his work and was banned from presenting research to the organization for the next two years, according to seven people familiar with the events, whose account of his ban was confirmed by the Oz campaign. Oz is now the Republican nominee for U.S. Senate in Pennsylvania.
He was also prohibited from publishing his work in the society’s medical journal for the same period of time, according to the people familiar with the events, four of whom recalled details of the controversy on the record.
“My understanding is it was the lack of really solid statistical analysis that called everything into question,” said one person who was sympathetic to Oz, saying he simply ran into funding and deadline problems.
My reply: Sure, why would anyone think that just cos someone’s a good surgeon, that they’d have any idea how to conduct research? I know lots of people who are really good at research but it’s not like they could do surgery.
The interesting thing to me is that last paragraph of the above quote, as it seems to reflect the attitude that statistics is just a bunch of paperwork, or a set of hoops to jump through. That attitude that researchers have, that their ideas are evidently correct and the statistics is just some rubber stamp.
With Oz, though, there’s another twist, given his later record of promoting miracle cures. It’s hard to imagine he really believes in all the things that he promotes—or maybe “belief” isn’t really the point; perhaps he just has a very general belief in the power of placebo, in which case anything he recommends would be automatically legit. Indeed, the more people pay for it, the more effective the placebo power is. Kinda like academic funding!
The fact that he was banned, and not just rejected, is disturbing and suggests there is more to it than just bad stats. Conferences are not exactly known for their selectivity. Even if someone had committed a major statistical blunder (like running t-tests on non-normal data) and submitted to a journal, I would recommend that their paper be rejected, not that they be banned for years. I can’t even imagine what he did to antagonize a conference so much that they banned him.
sorry–can’t help myself–“running t-tests on non-normal data” is actually 100% fine if you have a decent sample size, cuz of the central limit theorem.
This being Andrew Gelman’s blog, maybe the point is that is that running any null hypothesis test at all counts as a “major statistical blunder” ;)
I agree that this is a puzzling report. It is not unusual to get a rejection from a learned society. I have read my share of “Thank you for your submission, but we’re just too full to include your study” notes. A “don’t send anything for two years” inclusion is pretty unusual. Some editorial advice to punch up the statistical analysis is ordinarily intended to be helpful. I only read the teaser at the WaPo because I’m not a subscriber, and there might be some real damning stuff there; perhaps someone has more information.
I found that Oz’s show smacked of advocacy and even hucksterism not scientific analysis, but there has always been some of that in even the most high minded scientific journals in my field at least. We all need to improve our self policing to avoid blind advocacy, cheerleading, and self-promotion.
I remain as puzzled as oncodoc is. When I emailed the Washington Post article to Andrew, I was hoping that with Andrew’s Columbia University connection, he or one of the bloggers would enlighten me as to why Oz was reprimanded so severely. While I am prepared to believe the worst about Oz, I confess that the affair/punishment remains a mystery.
Paul:
I have no connections in Columbia’s surgery department! But I do have the general sense that the medical profession takes discipline pretty seriously at times (see for example here) so I’m not surprised that if a medical conference did have a finding of a violation of professional ethics, that they’d do something about it.
Well, my impression during a 48 year (and counting) career in health care is that the medical profession is actually pretty lax about violations of ethics in general. But when things are sufficiently egregious that they choose not to turn a blind eye, they tend towards severe sanctions. So my take is that Oz must have done something really awful to be disciplined in this way, certainly not just a bad statistical analysis.
Clyde:
Medicine may well be lax about ethics violations in an absolute sense, but I think they’re serious in comparison to other professions, or at least to other academic professions. I can’t think of any examples whatsoever of sanctions for ethics violations in statistics, political science, economics, or sociology, aside from cases of sexual harassment. I can’t think of any cases of formal sanctions for doing unethical statistical analysis, plagiarism, faking data, etc. I guess there must be some examples but it’s my sense that the medical profession is more serious about this, in that they have some procedures which occasionally are carried out.
But, sure, given Oz’s later behaviors such as endorsements of miracle cures, I can well believe he did something awful. I certainly wouldn’t trust him near any research.
“It’s hard to imagine he really believes in all the things that he promotes” When he was dragged to testify under oath on the subject he said that there is no such thing as a miracle cure, despite what he advocates on his show. It was a strange event because he (as I interpreted it) agreed that there is no such thing as a miracle cure or magic pill or whatever, but still thought that the products he regularly endorses as such were effective.
Cover by WaPo:
https://www.washingtonpost.com/news/the-fix/wp/2016/09/15/that-time-congress-railed-on-dr-oz-for-his-miracle-diet-pills/
If you are suffering from a deficiency, then getting the vitamin/mineral is indeed a “miracle cure”. The NNT for treating stuff like scurvy, beriberi, and rickets is ~1. For most medical interventions NNT is around 10-100,.
Suppose if you were a pirate in the 1500’s, you’d take care to pack some lemons on your boat. In modern times, the conditions you list are extremely rare, and prevented by eating a bowl of Cheerios in the morning.
Your example is historically inaccurate afaik, but sure. There were probably uneducated pirates in the 1500s who were better at figuring things out than tens of thousands of NHST-using researchers, funded with tens of billions of dollars each year, for the last seven decades.
I suggest you read some more history.
https://www.nationalgeographic.com/science/article/scurvy-disease-discovery-jonathan-lamb
https://en.wikipedia.org/wiki/Scurvy
My greater point wasn’t about NHST, but about how meaningless your point was. I’m wondering if you have been diagnosed with autism or a form of obsessive disorder? It would help explain your habit of warping almost any conversation on this blog around your pet interest/pet theory/obsession.
Severe forms are rare, but I’ve had vitamin C deficiency multiple times. It appears to be a risk due to atopic disease. Essentially hyperactive immune system/allergies leads to excessive oxidative stress. Symptoms are minor bruising often in lines along blood vessels and minor bleeding of gums. Taking vitamin c pills was indeed miraculous. And I had this in college even though I was routinely eating citrus fruit. Apparently some people just need a lot more vitamin c than others, and also the dining halls would leave the fruit out all day for multiple days, ultimately likely destroying the vitamin c content.
There are 7 billion people on the planet. If a middle class college educated American can get vitamin c deficiency, what is the global incidence?
Now, scurvy at the level experienced by seafarers in the 1500s is a different story.
Yep, miracle cures *do exist”. Apparently even uneducated pirates in the 1500s can figure them out.
But none have been discovered after ~1950 when NHST took over. No matter how many resources are thrown at a problem the best they can do is something that benefits 10% or less of the people who get treated. And the literature is biased toward “excessive optimism”.
It is amazing to see how low people’s standards are for medical interventions. If they simply demanded highly effective treatments the researchers would (collectively) go back to using science and start pumping out actual cures within a couple decades. Just like how it was ~1900-1950.
And the RDAs for vitamins/minerals are based on young healthy people. Extrapolating that to people who have chronic health issues or are just older makes no sense. It is like assuming a new house requires the same amount of wood/etc for maintenance as an old one or a house that got hit by a tornado.
Anonymous, sorry about your Vitamin C issues. I’m glad they were identified. Yes, Vitamin C deficiency–to the degree (~<11.4 umol/L) and length of time (~20-30 weeks) at which it presents clinically as scurvy is quite rare. In a records review across a 36-year time period, Mayo Clinic (across 3 of their major units) identified 11 subjects that presented with clinically manifested scurvy.
https://pubmed.ncbi.nlm.nih.gov/16911372/
The purpose of that paper is to tell people scurvy is being underdiagnosed, and how/when to check for it. That they found only seven cases is a problem.
It looks like 1-10% of people in wealthy countries and ~50% in low income countries meet the definition of deficient, and this increases in those most likely to show up at the doctor:
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7400810/
It is difficult and expensive to measure because it is such a reactive molecule though, so that may account for some of those apparent cases.
Btw, when I finally checked, I could also find no mention of pirates in the 1500s using citrus. What I found was consistent with my understanding, lemons (called “limes” at the time) were essentially a classified secret weapon used by the British Navy during the Napoleonic Wars.
But all this is besides the point that Vitamin c is a miracle cure for vitamin C deficiency, which is why scurvy is now so much rarer in populations that take advantage of that knowledge.
This supposed misbehavior occurred in 2003 and surfaces in 2022 just before the election. I am no more paranoid than the next man (provided the next man is Richard Nixon). Far worse is this gaffe of a week ago:
“At an October 25 2022 debate with John Fetterman, Mehmet Oz claimed that abortion should be decided by “a woman, her doctor, and local political leaders.”
Even Hershel Walker, “The Father of the Year”, did not go that far.