Study: Fraud growing in scientific research papers
WASHINGTON (AP) — Fraud in scientific research, while still rare, is growing at a troubling pace, a new study finds.
A review of retractions in medical and biological peer-reviewed journals finds the percentage of studies withdrawn because of fraud or suspected fraud has jumped substantially since the mid-1970s. In 1976, there were fewer than 10 fraud retractions for every 1 million studies published, compared with 96 retractions per million in 2007.
The study authors aren’t quite sure why this is happening. But they and outside experts point to pressure to hit it big in science, both for funding and attention, and to what seems to be a subtle increase in deception in overall society that science may simply be mirroring.
Note the bold. I was lambasted for saying essentially the same thing on PBS Newshour.
I wonder if Stephan Lewandowsky’s “moon landing denier conspiracy theory” paper will find itself in the fraud category now that Steve McIntyre has exposed the statistically shoddy sleight of hand:
McIntyre on Lewandowsky’s Fake Correlation
Steve McIntyre takes Lewandowsky’s statistical screed to task and writes:
Lewandowsky’s most recent blog post really makes one wonder about the qualifications at the University of West Anglia Western Australia.
Lewandowsky commenced his post as follows:
The science of statistics is all about differentiating signal from noise. This exercise is far from trivial: Although there is enough computing power in today’s laptops to churn out very sophisticated analyses, it is easily overlooked that data analysis is also a cognitive activity.
Numerical skills alone are often insufficient to understand a data set—indeed, number-crunching ability that’s unaccompanied by informed judgment can often do more harm than good.
This fact frequently becomes apparent in the climate arena, where the ability to use pivot tables in Excel or to do a simple linear regressions is often over-interpreted as deep statistical competence.
I mostly agree with this part of Lewandowsky’s comment, though I would not characterize statistics as merely “differentiating signal from noise”. In respect to his comment about regarding the ability to do a linear regression as deep competence, I presume that he was thinking here of his cousin institute, the University of East Anglia (UEA), where, in a Climategate email, Phil Jones was baffled as to how to calculate a linear trend on his own – with or without Excel. At Phil Jones’ UEA, someone who could carry out a linear regression must have seemed like a deity. Perhaps the situation is similar at Lewandowsky’s UWA. However, this is obviously not the case at Climate Audit, where many readers are accomplished and professional statisticians.
Actually, I’d be inclined to take Lewandowsky’s comment even further – adding that the ability to insert data into canned factor analysis or SEM algorithms (without understanding the mathematics of the underlying programs) is often “over-interpreted as deep statistical competence” – here Lewandowsky should look in the mirror.
Lewandowsky continued:
Two related problems and misconceptions appear to be pervasive: first, blog analysts have failed to differentiate between signal and noise, and second, no one who has toyed with our data has thus far exhibited any knowledge of the crucial notion of a latent construct or latent variable.
In today’s post, I’m going to comment on Lewandowsky’s first claim, while disputing his second claim. (Principal components, a frequent topic at this blog, are a form of latent variable analysis. Factor analysis is somewhat different but related algorithm. Anyone familiar with principal components – as many CA readers are by now – can readily grasp the style of algorithm, though not necessarily sharing Lewandowsky’s apparent reification.)
In respect to “signal vs noise”, Lewandowsky continued:
We use the item in our title, viz. that NASA faked the moon landing, for illustration. Several commentators have argued that the title was misleading because if one only considers level X of climate “skepticism” and level Y of moon endorsement, then there were none or only very few data points in that cell in the Excel spreadsheet.
Perhaps.
But that is drilling into the noise and ignoring the signal.
The signal turns out to be there and it is quite unambiguous: computing a Pearson correlation across all data points between the moon-landing item and HIV denial reveals a correlation of -.25. Likewise, for lung cancer, the correlation is -.23. Both are highly significant at p < .0000…0001 (the exact value is 10 -16, which is another way of saying that the probability of those correlations arising by chance is infinitesimally small).
These paragraphs are about as wrongheaded as anything you’ll ever read.
Read the rest here at Lewandowsky’s Fake Correlation
Discover more from Watts Up With That?
Subscribe to get the latest posts sent to your email.
Final paragraph in the linked article:
“..The study authors aren’t quite sure why this is happening…”
It may just be that they are easier to spot now due to the Internet, which will increase the trend outside of reality.
WASHINGTON (AP) — Fraud in scientific research, while still rare, is growing at a troubling pace, a new study finds.
A review of retractions in medical and biological peer-reviewed journals finds the percentage of studies withdrawn because of fraud or suspected fraud has jumped substantially since the mid-1970s. In 1976, there were fewer than 10 fraud retractions for every 1 million studies published, compared with 96 retractions per million in 2007.
The study authors aren’t quite sure why this is happening. But they and outside experts point to pressure to hit it big in science, both for funding and attention, and to what seems to be a subtle increase in deception in overall society that science may simply be mirroring.
Have Hansen or Mann retracted any of their papers?
A million studies published in 2007?! I never would have suspected that it was such a huge number. No wonder there’s so much competition for funding. I wonder how many of those are really quality work worthy of publishing? If a lot of them are like the majority of the medical studies I hear about (this or that statistically associated with an increase in disease xyz) then it’s probably a lot of make work. Sounds like science has become an industry. An increase in fraud under those conditions wouldn’t be a surprise.
Causation for increase in scientific fraud should be looked for in the ideologies that promote adding biased and arbitrarily subjective socialized qualities/ inputs onto unbiased objective scientific methods.
Look at the PNS ideology as a possible candidate for the causation of socialized and subjective scientific research by scientists with socio-political subjective value judgments that give rise to the reduced ethical performance of scientists.
John
It’s liberal indoctrination, I mean education, and their new post normal science combined with science for hire (grant money), greed, ego and a belief that activism is what scientists are supposed to do.
A man can get lung cancer without smoking ever. So smoking is not the only way to get it. I know many whom has smoked all lifespan from chidhood, without getting it. So is it true or false that: Smoking causes lung cancer?
Lewandowsky has lot of stupid questions. IQ probably 90?
Of greater concern to me is the amount of sheer rubbish that makes it through peer review and gets published. In one experiment I read about, the experimenter had apparently applied 6MW of power to a 1lb piece of steak for a minute in an attempt to sterilise the cut surfaces. Certainly he would have sterilised the entire piece of meat if so much power had actually been applied, but no one would have been interested in eating the remnants. This error would have been picked up if s/he done some basics, such as monitoring the current and voltage flowing during the actual experiment, or if any one associated with the work understood even basic electrical engineering. Needless to say, the authors were no longer responding to comments or questions relating to the paper, but it hadn’t been withdrawn……
We’ve been saying it all along. Think we’ll see a fix in our lifetimes..?
Follow the money.
“…and to what seems to be a subtle increase in deception in overall society that science may simply be mirroring.”
It’s always easier to blame society instead of the person you see in the mirror.
Could it be that the observed trend is due, at least in part, to advances in the ability to detect fraud? Maybe what this study means is that scientific research is becoming more transparent, and fraud is accordingly more difficult to get away with. After all, now that data is stored digitally, and we have the internet, it’s much easiest for the likes of Steve McIntyre to get their hands on it.
It’s pretty impotant to clarify the difference between “fraud” and incompetence or a disagreement about methodology or results. The term “fraud” applies only to the wilful (malicious) falsification of data or results to obtain a desirable end. It is wrong to ascribe to malice that which can be explained through incompetance, or through political disagreement.
I won’t deny there’s fraud in scientific publishing, or that it may be on the increase. I’m saying one needs to be very careful about what one is claiming is fraudulent. Always keep to the higher ground.
Anyone else see the irony here? Study finds increasing fraud by studies?
I must say that trying to debate the issues at the blog used by L. et al became increasingly difficult as the moderator started virtually random snips of content citing inflammatory comments.
Some other interesting quotes from the article, in addition to the one noted by Gary:
My theory is that the number of committed frauds in science is directly proportional the amount of money spent on climate science.
Fraud in scientific research, while still rare, is growing at a troubling pace, a new study finds.
>>>>>>>>>>>>>
So…. itz another hockey stick?
Darn things are creeping into science from every direction!
There is the possibility that scientific fraud is like bad weather.
When you have better access to the phenomena, you just notice it more often.
With little to no electronic access to scientific papers in 1976, it was incumbent on possible reviews of the studies, beyond the “peer review.” to actually go an buy the journals.
This study shows that journal article retractions are rare but growing at an alarming rate. Possibly fraud is a constant.
The “retractions” problem was discussed on this afternoon’s “Material World” on BBC Radio 4. I believe the following link will work worldwide (TV programmes are limited to the UK only, but most radio programmes don’t have that restriction.)
http://www.bbc.co.uk/iplayer/episode/b01n1rpr/Material_World_04_10_2012/
Steve McIntyre’s quotation of Lewandowsky and Oberauer is interesting in another way. It seeks to separate “scientific statistics” from Excel pivot tables. Their narrow definition of statistics being “all about differentiating signal from noise” should be compared to a more standard definition like :-
According to Lewandowsky only “scientists” can divine the truth by scientific statistics beyond the reach of everyone else. Those who use the low level Excel analysis cannot see that truth, despite all their clever analysis. As the main critic of the Lewandowsky paper who made extensive use of pivot table, I now show in my latest posting that my pivot tables highlighted some essential elements totally absent from the paper. For instance, the very small number of skeptic responses or the very small percentage of responses supporting the non-climate conspiracy theories. I also suggest that publication of this analysis would alter the media perception of the paper.
Finally, I suggest that low level statistics are a way of asking searching questions, for scientists, reviewers of scientific papers and the lay public.
Yes Fred, follow the money.
Only 96/million up til 2007? Obviously they need to look at climate papers a bit closer to the present. Where do I apply for a grant for this?
Let me help out…………..funding?
Here is a warning from the past about possible ‘future’ scams and rent seekers.
How did he know this was going to happen? What I want to know is when is the CAGW scam going to end?