Download Lectures on Biostatistics (1971). Corrected and searchable version of Google books edition
Download review of Lectures on Biostatistics (THES, 1973).
honesty
This piece is almost identical with today’s Spectator Health article.
This week there has been enormously wide coverage in the press for one of the worst papers on acupuncture that I’ve come across. As so often, the paper showed the opposite of what its title and press release, claimed. For another stunning example of this sleight of hand, try Acupuncturists show that acupuncture doesn’t work, but conclude the opposite: journal fails, published in the British Journal of General Practice).
Presumably the wide coverage was a result of the hyped-up press release issued by the journal, BMJ Acupuncture in Medicine. That is not the British Medical Journal of course, but it is, bafflingly, published by the BMJ Press group, and if you subscribe to press releases from the real BMJ. you also get them from Acupuncture in Medicine. The BMJ group should not be mixing up press releases about real medicine with press releases about quackery. There seems to be something about quackery that’s clickbait for the mainstream media.
As so often, the press release was shockingly misleading: It said
Acupuncture may alleviate babies’ excessive crying Needling twice weekly for 2 weeks reduced crying time significantly
This is totally untrue. Here’s why.
|
Luckily the Science Media Centre was on the case quickly: read their assessment. The paper made the most elementary of all statistical mistakes. It failed to make allowance for the jelly bean problem. The paper lists 24 different tests of statistical significance and focusses attention on three that happen to give a P value (just) less than 0.05, and so were declared to be "statistically significant". If you do enough tests, some are bound to come out “statistically significant” by chance. They are false postives, and the conclusions are as meaningless as “green jelly beans cause acne” in the cartoon. This is called P-hacking and it’s a well known cause of problems. It was evidently beyond the wit of the referees to notice this naive mistake. It’s very doubtful whether there is anything happening but random variability. And that’s before you even get to the problem of the weakness of the evidence provided by P values close to 0.05. There’s at least a 30% chance of such values being false positives, even if it were not for the jelly bean problem, and a lot more than 30% if the hypothesis being tested is implausible. I leave it to the reader to assess the plausibility of the hypothesis that a good way to stop a baby crying is to stick needles into the poor baby. If you want to know more about P values try Youtube or here, or here. |
|
One of the people asked for an opinion on the paper was George Lewith, the well-known apologist for all things quackish. He described the work as being a "good sized fastidious well conducted study ….. The outcome is clear". Thus showing an ignorance of statistics that would shame an undergraduate.
On the Today Programme, I was interviewed by the formidable John Humphrys, along with the mandatory member of the flat-earth society whom the BBC seems to feel obliged to invite along for "balance". In this case it was professional acupuncturist, Mike Cummings, who is an associate editor of the journal in which the paper appeared. Perhaps he’d read the Science media centre’s assessment before he came on, because he said, quite rightly, that
"in technical terms the study is negative" "the primary outcome did not turn out to be statistically significant"
to which Humphrys retorted, reasonably enough, “So it doesn’t work”. Cummings’ response to this was a lot of bluster about how unfair it was for NICE to expect a treatment to perform better than placebo. It was fascinating to hear Cummings admit that the press release by his own journal was simply wrong.
Listen to the interview here
Another obvious flaw of the study is that the nature of the control group. It is not stated very clearly but it seems that the baby was left alone with the acupuncturist for 10 minutes. A far better control would have been to have the baby cuddled by its mother, or by a nurse. That’s what was used by Olafsdottir et al (2001) in a study that showed cuddling worked just as well as another form of quackery, chiropractic, to stop babies crying.
Manufactured doubt is a potent weapon of the alternative medicine industry. It’s the same tactic as was used by the tobacco industry. You scrape together a few lousy papers like this one and use them to pretend that there’s a controversy. For years the tobacco industry used this tactic to try to persuade people that cigarettes didn’t give you cancer, and that nicotine wasn’t addictive. The main stream media obligingly invite the representatives of the industry who convey to the reader/listener that there is a controversy, when there isn’t.
Acupuncture is no longer controversial. It just doesn’t work -see Acupuncture is a theatrical placebo: the end of a myth. Try to imagine a pill that had been subjected to well over 3000 trials without anyone producing convincing evidence for a clinically useful effect. It would have been abandoned years ago. But by manufacturing doubt, the acupuncture industry has managed to keep its product in the news. Every paper on the subject ends with the words "more research is needed". No it isn’t.
Acupuncture is pre-scientific idea that was moribund everywhere, even in China, until it was revived by Mao Zedong as part of the appalling Great Proletarian Revolution. Now it is big business in China, and 100 percent of the clinical trials that come from China are positive.
if you believe them, you’ll truly believe anything.
Follow-up
29 January 2017
Soon after the Today programme in which we both appeared, the acupuncturist, Mike Cummings, posted his reaction to the programme. I thought it worth posting the original version in full. Its petulance and abusiveness are quite remarkable.
I thank Cummings for giving publicity to the video of our appearance, and for referring to my Wikipedia page. I leave it to the reader to judge my competence, and his, in the statistics of clinical trials. And it’s odd to be described as a "professional blogger" when the 400+ posts on dcscience.net don’t make a penny -in fact they cost me money. In contrast, he is the salaried medical director of the British Medical Acupuncture Society.
It’s very clear that he has no understanding of the error of the transposed conditional, nor even the mulltiple comparison problem (and neither, it seems, does he know the meaning of the word ‘protagonist’).
I ignored his piece, but several friends complained to the BMJ for allowing such abusive material on their blog site. As a result a few changes were made. The “baying mob” is still there, but the Wikipedia link has gone. I thought that readers might be interested to read the original unexpurgated version. It shows, better than I ever could, the weakness of the arguments of the alternative medicine community. To quote Upton Sinclair:
“It is difficult to get a man to understand something, when his salary depends upon his not understanding it.”
It also shows that the BBC still hasn’t learned the lessons in Steve Jones’ excellent “Review of impartiality and accuracy of the BBC’s coverage of science“. Every time I appear in such a programme, they feel obliged to invite a member of the flat earth society to propagate their make-believe.
Acupuncture for infantile colic – misdirection in the media or over-reaction from a sceptic blogger?26 Jan, 17 | by Dr Mike Cummings So there has been a big response to this paper press released by BMJ on behalf of the journal Acupuncture in Medicine. The response has been influenced by the usual characters – retired professors who are professional bloggers and vocal critics of anything in the realm of complementary medicine. They thrive on oiling up and flexing their EBM muscles for a baying mob of fellow sceptics (see my ‘stereotypical mental image’ here). Their target in this instant is a relatively small trial on acupuncture for infantile colic.[1] Deserving of being press released by virtue of being the largest to date in the field, but by no means because it gave a definitive answer to the question of the efficacy of acupuncture in the condition. We need to wait for an SR where the data from the 4 trials to date can be combined. So what about the research itself? I have already said that the trial was not definitive, but it was not a bad trial. It suffered from under-recruiting, which meant that it was underpowered in terms of the statistical analysis. But it was prospectively registered, had ethical approval and the protocol was published. Primary and secondary outcomes were clearly defined, and the only change from the published protocol was to combine the two acupuncture groups in an attempt to improve the statistical power because of under recruitment. The fact that this decision was made after the trial had begun means that the results would have to be considered speculative. For this reason the editors of Acupuncture in Medicine insisted on alteration of the language in which the conclusions were framed to reflect this level of uncertainty. DC has focussed on multiple statistical testing and p values. These are important considerations, and we could have insisted on more clarity in the paper. P values are a guide and the 0.05 level commonly adopted must be interpreted appropriately in the circumstances. In this paper there are no definitive conclusions, so the p values recorded are there to guide future hypothesis generation and trial design. There were over 50 p values reported in this paper, so by chance alone you must expect some to be below 0.05. If one is to claim statistical significance of an outcome at the 0.05 level, ie a 1:20 likelihood of the event happening by chance alone, you can only perform the test once. If you perform the test twice you must reduce the p value to 0.025 if you want to claim statistical significance of one or other of the tests. So now we must come to the predefined outcomes. They were clearly stated, and the results of these are the only ones relevant to the conclusions of the paper. The primary outcome was the relative reduction in total crying time (TC) at 2 weeks. There were two significance tests at this point for relative TC. For a statistically significant result, the p values would need to be less than or equal to 0.025 – neither was this low, hence my comment on the Radio 4 Today programme that this was technically a negative trial (more correctly ‘not a positive trial’ – it failed to disprove the null hypothesis ie that the samples were drawn from the same population and the acupuncture intervention did not change the population treated). Finally to the secondary outcome – this was the number of infants in each group who continued to fulfil the criteria for colic at the end of each intervention week. There were four tests of significance so we need to divide 0.05 by 4 to maintain the 1:20 chance of a random event ie only draw conclusions regarding statistical significance if any of the tests resulted in a p value at or below 0.0125. Two of the 4 tests were below this figure, so we say that the result is unlikely to have been chance alone in this case. With hindsight it might have been good to include this explanation in the paper itself, but as editors we must constantly balance how much we push authors to adjust their papers, and in this case the editor focussed on reducing the conclusions to being speculative rather than definitive. A significant result in a secondary outcome leads to a speculative conclusion that acupuncture ‘may’ be an effective treatment option… but further research will be needed etc… Now a final word on the 3000 plus acupuncture trials that DC loves to mention. His point is that there is no consistent evidence for acupuncture after over 3000 RCTs, so it clearly doesn’t work. He first quoted this figure in an editorial after discussing the largest, most statistically reliable meta-analysis to date – the Vickers et al IPDM.[2] DC admits that there is a small effect of acupuncture over sham, but follows the standard EBM mantra that it is too small to be clinically meaningful without ever considering the possibility that sham (gentle acupuncture plus context of acupuncture) can have clinically relevant effects when compared with conventional treatments. Perhaps now the best example of this is a network meta-analysis (NMA) using individual patient data (IPD), which clearly demonstrates benefits of sham acupuncture over usual care (a variety of best standard or usual care) in terms of health-related quality of life (HRQoL).[3] |
30 January 2017
I got an email from the BMJ asking me to take part in a BMJ Head-to-Head debate about acupuncture. I did one of these before, in 2007, but it generated more heat than light (the only good thing to come out of it was the joke about leprechauns). So here is my polite refusal.
|
Hello Thanks for the invitation, Perhaps you should read the piece that I wrote after the Today programme Why don’t you do these Head to Heads about genuine controversies? To do them about homeopathy or acupuncture is to fall for the “manufactured doubt” stratagem that was used so effectively by the tobacco industry to promote smoking. It’s the favourite tool of snake oil salesman too, and th BMJ should see that and not fall for their tricks. Such pieces night be good clickbait, but they are bad medicine and bad ethics. All the best David |
|
I had never intended to write about climate. It is too far from the things I know about. But recent events have unleashed a Palin-esque torrent of comments from people who clearly know even less about it than I do. In any case, it provides a good context to think about trust in science, |
 Earthrise from moon. (click to enlarge) |
My interest in it, apart from little matters like the future of the planet, lies in the reputation of science and scientists.
I have been going on for years now about the lack of trust in science, and the extent to which it is a self-inflicted problem. The latest reactions to the developments at the University of East Anglia and the IPCC may show the nature of the problem with dreadful clarity,
Many of us came into science because, apart from the sheer beauty of nature, it seemed like one of the few honest ways of earning a living. Most scientists that I know still think like that, but recent
events invite some reexamination of honesty in science.
How dishonest is science?
The first thing to say is that I have never come across anything in my own field that would qualify as fraud, or even dishonest. I did once have a visit from a rather distressed postdoc (not in my area of work) who felt pressurised by her boss into putting an interpretation on her work that she did not agree with. In the end, the bit of work in question was left out of the paper. That could be held to be dishonest, in that the omission wasn’t mentioned, but it could also be held that the omitted result was too ambiguous to contribute much to the paper. It was just short of the point where I’d have felt compelled to do something about it. But only just. That is about the worst thing I’ve encountered in a lifetime.
There is, of course, an enormous difference between being wrong and being dishonest. Any research that is worth doing has an outcome that can’t be predicted before the work is done. At best, one can hope for an approximation to the truth. Mistakes in observations, analysis or interpretation will sometimmes mean the announced result is completely wrong, with no trace of dishonesty being involved. But when that happens, others soon fiind the mistake. It is that self-correcting characteristic of science that keeps it honest in the long run.
Of course there have been occasional cases of outright fraud, simple
falsification or fabrication of data. How often it occurs is not really known. There is a recent analysis in PLoS One, about verified cases of misconduct in the USA suggested that 1 in 100,000 scientists per year are to blame, but other ways of counting give larger numbers. For example, if asked around 2 in 100 scientists claim to be aware of misconduct by someone else., The numbers aren’t huge but they are much bigger than they should be.
It isn’t perhaps surprising that the Fanelli study found misconduct was most frequent in “medical (including clinical and pharmacological) research studies”, which are often funded by the pharmaceutical industry, Basic biomedical research and other subjects were better, though sadly that could be only because they are less often offered money.
What gives rise to dishonesty?
It seems obvious that one motive is money, as suggested by the worst rates of misconduct being found in the clinical pharmacological studies, It is well known that studies funded by industry are more likely to produce results that favour the product than those funded in other ways.
The other reason is presumably the human desire to win fame, promotion and to get grants.
It is no excuse, but it is perhaps a reason for misconduct that the pressure to publish and produce results is now enormous in academia. Even in good universities people are judged by the numbers (rather than the quality) of papers they produce and by what journal they happen to be published in. Contrary to public perception, even quite senior people have no guarantee that they can’t be fired, and life for postdoctoral fellows, who do a large fraction of experimental research, is harsh to the point of cruelty. They exist on a series of short term contracts, they work exceedigly hard and have poor prospects of getting a secure job. In conditions like that, the only surprising thing is that there is so little dishonesty.
The pressure to publish in particular journals is particularly invidious because it is known that the number of citations that a paper gets (itself a fallible measure of quality) is independent of the journal in which it appears. Bibliometrists are the curse of our age. (See, for example Challenging the tyranny of impact factors, 2003; and How to get good science, 2007 or its web version; and Peter Lawrence’s article, The mismeasurement of science)
The enormous competitive pressure under which academics work is imposed by vice-chancellors, research councils and other senior people who should know better, It is a self-inflicted wound.
In other words, the authorities provide a strong incentive to do poor, over-hurried and occasionally dishonest science. Perhaps the surprising thing in the circumstances is that there is so little outright fabrication. The very measures that have the aim of improving science actually have just the opposite effect. That is what happens when science is run by people who don’t do it.
For an idea of what life is like in science now, try Peter Lawrence’s Real Lives and White Lies in the Funding of Scientific Research. Or, for someone at the other end of their career, Jennifer Rohn’s account on Nature blogs.
Given the high degree of insecurity for young researchers, compounded by well-intentioned but vacuous “training” from daft Robert’s’ "training courses", or the dismaly ineffective Concordat, the only surprise is that so many people remain honest and devoted to good science. Nothing raises the ire of hard-pressed scientists more than the constant emails form HR trying to force people to go to gobbledygook courses on "wellbeing". Times Higher Education recently did a piece on "Get happy", The comments are worth reading.
So what about climate change?
Out of thousands of pages in the IPCC reports, a single mistake was found, On page 493 of the IPCC’s second 1000-page Working Group report on “Impacts, Adaptation and Vulnerability” (WGII) it was said that Himalayan glaciers were “very likely” to disappear by 2035. Glaciers are melting but that date can’t be justified. This single mistake has been blown out of all proportion. Furthermore it is important to notice that the mistake was found by scientists, not by ‘sceptics’. It is a good example of the self-correcting nature of science. Nevertheless this single mistake has provoked something close to hysteria among those who want to deny that something needs to be done.
On the other hand, the hacked emails from the University of East Anglia (UEA) look bad. It simply isn’t possible at the moment to say whether they are as bad as they seem at first sight, We just don’t know whether anything of importance was concealed, but we should know.
One thing can be said with certainty, and that is that the reaction to their revelation by Dr Phil Jones, and by the vice-chancellor of the University of East Anglia, was nothing short of disastrous. Fred Pearce put it very well in Climate emails cannot destroy proof that humans are warming the planet
Most unforgivably of all, UEA refused to comply with requests under the Freedom of Information Act, and there is some reason to think that relevant material was deleted. The deputy information commissioner, Graham Smith, said: in a statement that
“The emails which are now public reveal that Mr Holland’s requests under the Freedom of Information Act were not dealt with as they should have been under the legislation. Section 77 of the Freedom of Information Act makes it an offence for public authorities to act so as to prevent intentionally the disclosure of requested information.”.
That seems to me to be a matter that requires the resignation of the vice-chancellor. On this matter, I think George Monbiot is spot on in his article “Climate change email scandal shames the university and requires resignations“.
There was a big feature about academic freedom in Times Higher Education recently. One of the problems was what happens to someone who brings their own university into disrepute. But when that term is used, it is always used about junior partners in the organisation (you know, professors and the like). It should apply equally to heads of communications and vice-chancellors who bring their own university into disrepute, whether the disrepute is brought about by failing to comply with the Freedom of Information Act, or by promoting courses in junk medicine.
In general, conspiracy theories are wrong. I’m not sure how much of the distortion of climate data results from surreptitious funding of opposition to doing anything by the fossil fuel industry. The Royal Society is an organisation that is not usually prone to conspiritorialist views. That means one must take it seriously the fact that in 2006, the Royal Society wrote to ExxonnMobil to ask them to stop funding climate denialist organisations. This is a bit like the way Big Pharma has been caught funding “user groups” that endorse their products. Some newspapers like to stir up controversies about things that aren’t very controversial. For example there is a good analysis of a recent Sunday Times piece here.
Of course it is often alleged that "quackbusters" are funded by Big Pharma, though in fact the amounts of money involved are far too small for Big Pharma to bother. Climate deniers too like to suggest that there is some sort of conspiracy, arranged between hundreds of labs in the world to conceal the fact that there is no such thing as warming. I guess that shows only that deniers know little about how science works. it is an exceedingly competitive business, and getting hundreds of labs to say the same thing would be like trying to herd cats.
If there is a problem, it is the other way round. Labs are in such intense competition with each other, that it lcan lead to undesirable levels of secrecy.
Blogs in which researches have a direct dialogue with the public are a big help. As always in the blogosphere, the problem is to find the reliable sources. Two excellent sites, in which scientists (not journalists or lobbyists) talk directly with the public are realclimate.org and Andrew Russell’s blog. The post on RealClimate, IPCC errors: facts and spin, is especially worth reading.
Total openness is the only cure
All the raw data and all emails have to be disclosed openly. Everything should be put on the web as soon as possible. By appearing to go to ground, UEA has made enormous problems for itself and for the rest of the world. Some people object to total openness on the grounds that the other side tells lies. In the case of climate change (and in the case of junk medicine too) that is undoubtedly true. The opponents are ruthlessly dishonest about facts. The only way to counter that is by being ruthlessly and visibly honest about what you know, and why.
The UK’s Meteorological Office has, to its great credit, put raw data on line. That policy has already paid off, because a science blogger found a mistake in the way that some Australian data had been incorporated into forecasts. The Met Office thanked him and corrected the mistake. In fact the error makes no substantial difference to the warming trend, but the principle is just great. The more people who can check analyses and eliminate slip-ups the better.
Putting raw data on the web is an idea that has been gathering force for a while, in all areas of work, not just climate change. In my own are (stochastic properties of single ion channel molecules) our analysis programs have always been available on the web, free to anyone who wants them, despite the large amount of work that has gone into them. And we run a course. almost free, on the theory that underlies our analyses. Within the last couple of months we have been discussion ways of making public all our raw data (in any case, we would always have sent it to anyone who asked). Digitised single channel records are big files (around 100 Mb) and it is only recently that the web has been able to deal with such large amounts of raw data. There are also problems of how to format data so other people can read it, The way we are all heading is clear, and the fact that some people in climate science appeared to be hiding raw data is a disgrace.
Public relations is not the cure
,
It is not uncommon to read that science needs better PR. That is precisely what is not needed. PR exists to put only one side of the story. That makes it an essentially dishonest occupation. Its aims are the very opposite of those of science. The public aren’t stupid: often they recognise when they are getting half the story.
It is particularly unfortunate that many universities have developed departments with names like "corporate communications". Externally they are seen as giving information about science, and indeed some of the things they do are successful public engagement in science. Only too often, though, it is made clear internally that an important aim of these departments is to improve the image of the university.
But you have to choose. You can engage the public in science or you can be a PR image-builder. You can’t be both.
The matter came to a head in 2008 when, according to a report in Times Higher Education, the University of Nottingham issued a memo that defined public engagement as: “The range of activities of which the primary functions are to raise awareness of the university’s capabilities, expertise and profile to those not already engaged with the institution”.
The mainstream media and political blogs
The biggest problem of all with climate change is that it has become more about politics than about facts. It has become an essential credential for any conservative to deny that climate is changing. It is part of their public image, and most conservatives neither know nor care about evidence. Like Sarah Palin, they just know. In the USA especially, the argument is not really about climate at all. It is really about discrediting Barack Obama -a sort of swift-boat treatment that uses whatever lies are needed.
Just as with the great MMR fiasco and the promotion of its false link to autism, reports in newspapers and blogs must bear much of the blame for failing to inform readers of the actual underlying facts and, just as important, the uncertainties. Of course some papers have done a pretty good job, particularly the Guardian and the Independent in the UK, and the New York Times.. The political blogs, by and large, haven’t. The Huffington Post has made little effort (and publishes some appalling nonsense about medicine too).
The problem with political blogs and tabloid newspapers is that they are much more interested in sensation and circulation than they are in giving accurate news and information. Take, for example, the Guido Fawkes blog. To be fair, the blog itself says "The primary motivation for the creation of the blog was purely to make mischief at the expense of politicians and for the author’s own self-gratification. Its writer", so you know not to expect much, Paul Staines, was at the Westminster Skeptics event, Does Political Blogging Make a Difference? He makes no pretence of taking the news seriously, which, I guess, is why I don’t read his blog. After the talks I asked why his blog did little about climate change. His answer was "where are your sandals?". On the way home I tweeted, from a very overcrowded train (most trains from Euston being cancelled that night),
"On way home from #sitp political blogging. Learned that Guido serious about nothing but Guido. Narcissist not journalist."
At least one other person there agreed (thanks, Dave Cole).
It was good to hear Sunny Hundall of Liberal Conspiracy (the only one I read), but I found myself agreeing mostly with the chair, Nick Cohen. It would be a tragedy if the great national and local papers were to vanish. Guido Fawkes and Huffington Post are not remotely like proper newspapers.
Specialist blogs like this one are fine if you are interested in the topics we write about, but we don’t begin to supplant proper newspapers. Bloggers can and do occasionally get good stories. Those that are written by scientists can analyse more critically than most journalists have either the knowledge or the time to do. Bur they don’t come close to supplanting the detailed reporting in good newspapers of local events, what happens in law courts or in parliament. That’s why it is vital to buy newspapers, not just read them free on the web.
Follow-up
James Hayton, who is in nanoscience has posted his thoughts obout trust in science on his blog. I discovered this via Twitter (@James_Hayton). He also posted a beautiful clip from the Ascent of Man, in which Jacob Bronowski speaks, from Auschwitz, of the consequences of irrational dogma. I’m old enough to remember Bronowski on a 1950s radio programme, the Brains Trust, though James Hayton clearly isn’t. Now I enjoy equally his daughter, Lisa Jardine‘s talks about science and history.
1 March 2010. Phil Jones, and the vice-chancellor of the University of East Anglia, appeared before a parliamentary committee. I found their responses to questions very disappointing. The evidence submitted by the Institute of Physics was strongly worded, but spot on.
“The CRU e-mails as published on the internet provide prima facie evidence of determined and co-ordinated refusals to comply with honourable scientific traditions and freedom of information law. The principle that scientists should be willing to expose their ideas and results to independent testing and replication by others, which requires the open exchange of data, procedures and materials, is vital.”
7 March 2010. Thanks to some kind remarks from Michael Kenward (see first comment). I sought wider coverage of this item in the mainstream media. Consequently, on Thursday 4 March, a much shortened version of this article appeared on the Guardian environment site. That piece has accumulated so far, 230 comments. The discussion of it has spread to the two blogs that I recommended, Andy Russell’s blog and RealClimate.org, though it has been diverted onto the side-issue of the letter from the Institute of Physics. The seemingly innocent idea that total openness would increase trust has, to my real astonishment, resulted in hysterical accusations that I’m a crypto-denialist. The constant politically-motivated attacks on climate science seem to have induced a paranoid siege mentality in some of them. There is a real danger that such people will harm their own cause, and that would be tragic.