Damned statistics

Further to the interesting discussions in these pages about statistics and epidemiology, here is a recent letter published in The Spectator (not available online). The correspondent goes a little further in his criticisms than I would, nevertheless, it bears repeating...

Sir,

As an engineer, scientist and mathematician, I am completely in agreement with Rod Liddle's view  of statistics. I have long argued, with anyone who cares to listen (and plenty who don't), that any statistic should be completely ignored if it doesn't come with a 1,000-page manual describing exactly how it was arrived at and what it means. And that manual should be read, pored over and discussed for at least ten years.

The human race has survived and flourished for hundreds of thousands of years without statistics. We survive using superstition, lust, greed and envy. All that statistics have done is make life miserable by legitimising with dubious science the personal biases of busybodies. It tells us that we shouldn't drink, shouldn't smoke and shouldn't immunise our children with the MMR vaccine. Lie, damned lies and statistics.

Dr Tom Roberts
Derby

Share

Tweet

Quote of the day...

...is from Paul at Smokles:

You know, sometimes I feel a little bad about singling out Winickoff, but its just like that whack a weasel game, and his head just keeps popping up.

This being Jonathan WhenIcough Winickoff, the ambitious paediatrician who popularised 'thirdhand smoke' and is now making some truly bizarre claims about secondhand smoke. Does this guy really exist or has he been invented to make Stan Glantz look reasonable?

Whatever the case, we better get used to this rising star. Last month in Vancouver he launched no fewer than NINE new papers.

Share

Tweet

Back in that London

Later today (Tuesday) I'll be in the green pastures of ol' London town for the last of the Voices of Freedom debates. Your panel, ladies and gentlemen, is...


James Delingpole (writer, journalist and broadcaster)
Julian Harris (chairman, Liberal Vision)
Chris Mounsey (leader, Libertarian party)
Brendan O’Neill (editor, Spiked!)
Mark Pack (co-editor, Liberal Democrat Voice) and
Paul Staines (aka blogger Guido Fawkes)
Michael White (assistant editor, Guardian)

All chaired by Mark Littlewood, director general of the Institute of Economic Affairs.

If you're there, come and say hello.

Share

Tweet

Junk scientists wanted

When it comes to tobacco control, it often seems that the policy is decided first and the science is produced as an afterthought. Since the lion's shares of the anti-smoking policies we see today were planned as far back as the 1970s, it is a remarkable coincidence that scientific evidence for each of them appeared at regular and timely intervals in the intervening years. This is something that The Economist gently hinted at in a recent review of a book called Merchants of Doubt:

In most of these campaigns the dissenters have argued that the American scientific establishment is tainted with an anti-corporate liberalism and is trying to impose socialism by the back door. One does not have to agree with this view, or to think that both sides are equally culpable, to feel that the ways in which science is used to generate assent for environmental action may sometimes be as interesting as the ways in which it is mobilised for dissent.

Though the authors note as a curiosity that campaigns against secondary smoke predated evidence that it did any harm, they show no desire to explore this seemingly reversed causality.

 

Secondhand smoke is old news in California these days, of course. These days, if you're an anti-smoking campaigner, your policy objectives are to ban smoking in the home and in the street. These 'next logical steps' have long since been settled on by the people who really matter—ie. you and your fellow 'health professionals'. All you need is a scientific fig-leaf to help you get around the quaint objections of personal liberty and individual sovereignty, which some politicians still consider important and which even you, as a citizen of a liberal democracy, feel compelled to pay lip-service to.

Of course, there isn't any serious scientific evidence that secondhand smoke from outdoors—or from next door—has the slightest effect on the health of others. Nor will there ever be. It would defy everything we know about toxicology, chemistry and biology, not to mention common sense. It's an idea of profound lunacy.

The best of a bad bunch of pseudo-scientific arguments for outdoor smoking bans are the risible notion of people being harmed by trace levels of toxins clinging to clothes and carpets ('thirdhand smoke') and the equally risible idea of cigarette butts leaching trace levels of toxins into the ground, thereby harming...er...something. 

It's not very promising, I'll grant you, but it's all there is and the lack of scientific evidence is holding things up. And so, if you're California's Tobacco-Related Disease Research Program, you wave some money in the air—the traditional mating call of the quackademic—and see who responds. Hence:

TRDRP Call for Applications

Request for Proposals for TRDRP Initiative on Thirdhand Smoke and Cigarette Butts

The Tobacco-Related Disease Research Program (TRDRP) announces a Request for Proposals (RFP) to undertake studies on Thirdhand Smoke and Cigarette Butt Waste, under a new initiative.

And, if you are sitting down...

Approximately $3.75 million is expected to be available for this RFP.

That should get a response from the scientific community in these troubled economic times, wouldn't you say?

The aim of this project is, according to the TRDRP...

...to conduct research on (1) the impact of thirdhand tobacco smoke exposure from indoor surfaces and air quality on public health, and (2) the effects of water and soil contamination by cigarette butts on organisms and humans.

This talk of 'conducting research' makes it sound as if some sort of impartial investigation into science is in the offing here. Tellingly, however, in the 15 page document which gives details about the project, the word 'science' isn't used once. The word 'policy', on the other hand, is used 14 times. That's a pretty good guide to the rest of the document.

They do, however, admit that there is no existing evidence to support either proposition.

The health effects of thirdhand smoke are poorly understood.

Virtually nothing is known about the impact of cigarette butts on contamination of air, water and soil.

Very true. That being the case, you wouldn't want to make any assumption that thirdhand smoke is dangerous, would you?

1.1 Thirdhand Smoke Exposure and Health Effects

The indoor surfaces and air quality component of this initiative is intended to help create and sustain a new research niche and infrastructure in California that is expected to shed light on several concrete aspects of the public health dangers of thirdhand smoke. 

And you wouldn't want to lead the researcher towards a particular conclusion or imply that you're looking for any particular outcome. Would you?

The findings from this research may have broad implications in policy enactment in California to prevent human exposure to thirdhand smoke in homes, hotels, apartment buildings, personal vehicles, gaming casinos, and hookah bars. 

It is anticipated that the research outcomes will contribute to dramatically reducing the exposure of developing and newborn infants, young children, adolescent youth, and adults to potential disease-causing toxicants produced from thirdhand smoke.

And you certainly wouldn't want to suggest that the whole project is specifically designed to meet predetermined political objectives. After all, how could you—the research hasn't even begun yet. Right?

Policy Implications

How will the scientific evidence from exposure to thirdhand smoke and cigarette butt pollution emanating from the proposed collaborative studies inform the policy makers to frame new policy in California to mitigate the public health effects?

How will these studies impact indoor air quality in buildings and vehicles to protect vulnerable populations from exposure risks? Strengths of proposed strategy for investigative plans to interface with policy makers and community advocates will be evaluated by reviewers.

... Funded investigators may be called upon to provide testimony to California legislators and to collaborate with policy researchers to help enact and enforce policies in California to mitigate the health effects of exposure to thirdhand smoke and cigarette butt pollution of water and soil in California.

It sounds a pretty sweet deal—the TRDRP provides the conclusion and the researcher fills in the blanks. All we need is someone prepared to prostitute their scientific integrity for a huge pile of cash. And let's look at all that lovely money again...

The TRDRP has allocated up to $3.75 million over three years for this RFP. It is anticipated that TRDRP may fund up to two (2) Grants of up to $425,000 each, or may fund one (1) Grant of up to $850,000 (including direct and indirect costs) per year for three (3) years to investigate the chemicals, biology and health risk assessment of thirdhand smoke.

What kind of person are we looking for anyway? A project like this would require someone highly trained in toxicology and the physical sciences, no?

A successful application will demonstrate in the Key Personnel a diverse tobacco-related disease and control expertise that is consistent with the proposed aims in the identified two or three themed areas, such as basic, translational and (if applicable) clinical expertise including chemists, biological chemists, cellular and molecular toxicologists...

Fair enough.

...engineers...

Sounds like a job for the great mechanical engineer Stanton Glantz. He's no stranger to a TRDRP handout, plus he lives locally. Get him on the phone.

...physicists, physicians, psychologists...

Psychologists like Georg Matt, for example? He lives nearby too.

...healthcare and tobacco control professionals...

Those three magic words: tobacco control professionals. Gentlemen, the bank is open for business.

...epidemiologists, health economists, statisticians and modeling experts, etc.

Okay, we get it. Pretty much anyone can apply. Fill your boots guys. And just in case your consciences are niggling at you, remember...

Approximately $3.75 million is expected to be available for this RFP.

Okay? Sleep well.

Share

Tweet

Medieval maximum

I'm currently reading Iain Gately's Drink: A Cultural History of Alcohol, an astonishingly thorough history of the world through the eyes of drinkers. In particular, my eyes were drawn to this passage regarding 13th Century England:

Ale was so vital to the very existence of the third estate that its price and quality were regulated by law. In 1267, King Henry III issued a pioneering piece of consumer protection legislation—the Assize of Bread and Ale—which set the maximum retail price of town-brewed ale at one penny for two gallons; the same penny bought three gallons from a country brewer. Prices were to be reviewed each year and could be adjusted in accordance with fluctuations in the cost of grain.

How times change, eh? Henry III would surely approve of Cooking Lager's campaign to 'Make it the Maximum'.

Share

Tweet

Die another day

In a recent post, I asked why the number of 'preventable' deaths seem to add up to more than the number of actual deaths. The answer, in a nutshell, is that you can only die once but your death can be prevented many times. In the comments, Carl V. Phillips explained how it works. I repeat his comments here in case you missed them, and because I have a feeling I'll be referring to them again in the future. 

While I certainly agree with you that some or all of the "blame the victim" body count estimates are high, be careful about this criticism -- it is not legitimate. Diseases and deaths always have multiple component causes, all of which can legitimately be called the cause (which is to say a necessary -- not sufficient -- cause of that death or disease at the particular time). 

So an individual may well die from smoking AND obesity AND eating junk food, and it is perfectly legitimate to say that had any one of these conditions been eliminated the death would not have occurred so soon. Someone who was killed by a drunk driver because a medical error prevented him from being saved in the hospital is a death due to alcohol use, motorized transport, and medical errors, so the causes add up to 3 for the one death. Thus, there is no reason to expect they would add up to the total. Indeed, they should add up to well more than the total if you have a rich enough list of causes.

I agree that this may not be how the man on the street interprets it, though I suspect if pushed that man would not actually be able to clearly state what he thinks it means. That is one of the problems with reciting raw scientific information to people who do not understand the science. Most people do not understand a relative risk statistic, but are barraged with them. But even descriptive statistics -- which most people probably think they understand at first blush -- are subtle. Nothing causes a fraction of a death -- it either causes it or not (see below). There is no obvious way to assign fractions.

As for bringing a death forward by merely one day, that is a fundamentally different question. And, yes, you could argue that a death that is accelerated by just one day by a particular cause should not be attributed to that cause for purposes of assessing public health statistics.

Wouldn't the word "factor" be more appropriate than "cause"? No. Cause is exactly the right word. It is the right word in the science of epidemiology (which is the source of this information) and is also the right word based on the usual intuitive definition. The latter, which is technically translated in epidemiology and most other sciences, is that in the absence of the particular influence, the particular outcome would not have occurred.

The word "factor" is one of those that often gets used because someone does not want to admit that they are making causal claims, even though that is exactly what they are doing. It doe not really mean anything. E.g., the phrase "risk factor", as used, has at least three or four different very distinct meanings, and therefore is worse than useless.

Following the above, it is easy to see why everything has multiple causes. Every death was caused by not only some disease, but also by birth of the individual in question, the evolution of humanity, the big bang, etc. This is part of why assigning fractions would not make sense, as noted above.

Angry Exile said:

And if a smoker goes outside the pub for a fag in winter and as a result of the alcohol passes out and subsequently carks it of hypothermia who gets to put their statistics up by one? ASH, Alcohol Concern or the Met Office?

If the individual would not have gone outside absent his smoking habit, then, yes, smoking caused his death, as did the alcohol that caused him to pass out, the weather that caused those to result in hypothermia, as well as, perhaps, his failure to put on a coat, his companion's failure to look for him after he disappeared, cutbacks on foot patrols by the police, and any number of other things.

The summary point is very simple: Everything has an infinite multitude of causes. For a particular outcome (e.g., death) we typically identify a particular set of them as the causes we are interested in intervening on (e.g., drug use, diet, medical tech), but there is nothing magical about that list. There is no reason to expect that those causes will not overlap in many cases, and once that list is made rich enough, overlap is inevitable.

Dr Phillips has recently started a new blog here.

Share

Tweet

Faulty logic

Dick Puddlecote has drawn my attention to this news story in the Daily Record, which is short enough to quote in full:

Booze price hike would lead to cheaper food, claims health watchdog

Hiking booze prices will force shops to slash the cost of food - and lead to greater state benefits, say a health watchdog.

Critics have claimed the Scottish government's plan will hit the poorest families.

But the National Institute for Health and Clinical Excellence believe that if supermarkets cannot entice customers with cut-price booze, they will use food as "loss leaders" instead.

And they say pricier alcohol will push up the Retail Prices Index - which determines benefits and state pensions.

Report author Anne Ludbrook, an Aberdeen University professor, said: "People on low incomes could be better off."

Far be it from me to argue with a professor of 'health economics' but I can see one or two problems with this...

Firstly, as I've said before, I'm quite sceptical about whether supermarkets really sell much alcohol below below cost price (ie. as a loss leader). That's mainly because I've never seen these cheap deals with my own eyes. On the other hand, I've never heard a supermarket explicitly deny doing it, and I don't know exactly what the wholesale price for a can of Heineken is, so let's assume it happens.

If it does, then surely the point is to draw people in with cheap booze and then get them to buy the core product, ie. food.

But if, as Ms. Ludbrook suggests, they sell food below cost price, that's not a loss leader, that's just making a loss. You've got nothing to lead them to.

Secondly, if you want to increase state benefits and pensions, then just campaign for that. Why go round the houses trying to making alcohol more expensive in order to (slightly) increase inflation? Besides which, food is also included in the Retail Price Index and the price of that—supposedly—is going to be "slashed".

Any anyway, people on benefits drink too, so the money you contrive to give them by increasing their benefits is going to be cancelled out by the extra money you force them to pay for their booze.

Share

Tweet