Monthly Archives: April 2011

Unhealthful News 113 – Dishonest time-series analysis (more interesting than it sounds)

It was suggested to me that I write about this story in which the UK Office for National Statistics released an incorrect report that said that the rate of heavy drinking among women had increased by about 20% over a decade.  The problem was that the methodology for measuring how much wine is in “one glass” changed in 2006, to reflect a belated recognition that the average serving of wine had, for a while, been larger than it was being counted as in the statistics.  It turns out that this adjustment – such that someone who says “I drink two glasses of wine per day” is now counted as consuming more total alcohol than someone giving the same answer in 2005 – accounts for more than the entire supposed increase.  That is, the real trend has been downward, but the recorded data shows the inevitable huge artificial jump for women (who drink a much larger portion of their alcohol in the form of wine) at the time of the adjustment.

I was not going to write about this because others covered it very nicely and my first thought was that I had little to add to what had been written (this one is particularly good and is at a great blog about beer, and it links to the two other good ones).  These other bloggers noted in particular that the ONS had previously attached a note to their own statistics reminding users/readers that the adjustment in 2006 needed to be considered when analyzing the data, and that when the new report was aggressively challenged, they appended a retraction of the erroneous claim and apology.  But, the bloggers also note, as far as they could find, none of the press outlets that breathlessly reported the original claim have printed a retraction.

The reason I decided to write about this was that I read about another possible example to watch out for;  I was sure there would be a third if I waited a few more days, but not so far, so I decided to run with the two.  The other example, reported by the CAGE blog, starts with the observation that in 2008 India adjusted their body mass index cutpoint between “normal” and “overweight” down from 25 to 23.  Just to put that in perspective, many Western countries adjusted “normal” down to 25 earlier in the decade, where it remains; even this is so low as to be meaningless, roughly translating into a reasonably muscular man of average height being “overweight” if he is carrying only about six or eight kilograms more fat than someone who would be described as skinny or is at body-sculpting levels of fat.  CAGE predicted in 2008 that this would lead to the claim that there is an increase in obesity in India and are now saying that this has happened.  They did not actually find a smoking-gun report of a time series that ignored the adjustment like the ONS case, but they reported news that hints that people are making that mistake less formally.

Unlike the British cutpoint for women drinking too much alcohol, which at least is just (just!) into the range that is believed to start to be harmful, the BMI cutpoint of 25, let alone 23, is well below the start of the range that has been shown to be unhealthy.  The measure just makes no sense at all.  It was interesting that the Times of India article CAGE linked to in their 2008 post said, “Doctors say these guidelines are the need of the hour since the number of those suffering from obesity and related problems is on a rise,” (as if the bizarre definition change would somehow help people who were actually obese) and made various hand-waving statements about Indians being somehow different from other H.sapiens.  While there is no direct connection, this strikes me as strangely similar to the reports of India trying to ban their incredibly popular dip products (oral smokeless tobacco and non-tobacco products) that I have written about over the last few weeks.  It is hard not to get the impression that the elites in India think that because of their unusual history and head count that they can just decide their part of the world works differently than the rest of it.

(Yes, I know, it is pretty rich for an American to be chiding someone else for practicing nationalistic exceptionalism.  The only defense I can offer is that most of those who make claims about American exceptionalism seem not to suggest that the rules of economics or biology affect us differently, but rather stick to claims about exceptionalism in ethics and socio-political matters, which are at least theoretically defensible though are quit dubious in practice.)

Anyway, the take-away points about these statistical adjustments are the following:  Changes in definitions like this occur all the time, and they are not difficult to deal with.  The two examples presented here are utterly trivial to deal with since they are just a change in labeling; someone doing a time series analysis today can just convert pre-change statistics to post-change ones (or vice versa) and report a consistent number.  That is, if someone wants to report the time trend in British drinking that runs through 2006 all they have to do is recalculate the pre-2006 quantities based on the post-2006 definition of “a glass”.  If they want to measure the increase in “overweight” in India, it is easy to apply the silly new definition to old BMI measures.  In other cases there is a shock to the data that is not just an arbitrary change in how to label the data, such as when the phrasing of a standard survey question changes in a way that gets radically different answers, often because no one realized the change would matter (e.g., if the “same” survey changes from asking men “did you have gay sex in the last year” to asking “did you had sex (including oral) with a man in the last year”, there will be a huge jump that cannot be corrected in the same way as a changed interpretation of the data).  In that case, the standard approach is to put in a variable that is whether an observation came before and after the change, which basically means assuming the time trend is continuous and that the jump that year is an artifact.  The same method can be used for a case like the wine or BMI if you only have the definition (you have the label “overweight” or “normal”, but not the actual BMI number), though in that case if you are doing a study and sending out a press release (as ONS did), there is no excuse for not going back and looking at the raw numerical data.

Given how simple this is, and that it is probably taught in the second or maybe even first semester of any decent applied statistics program, there is no excuse for the British study.  This is not something that an even slightly competent researcher could possibly fail to notice in the data even if they somehow overlooked the information about how the definition changed (“hmm, lets’ look at the trend from year to year: down a bit, down a bit, same, down a bit, huge increase, down a bit, down a bit – yup, it sure looks like an upward tend to me”).  Either someone was intentionally trying to mislead their audience or they were in so far over their heads – and by this I mean they knew absolutely nothing about analyzing statistics, but did so anyway – that they had no excuse for claiming their analysis was worth anything.  Either way, it is important to recognize the difference between honest disagreement (which this obviously was not, since the ONS retracted it), honest mistakes (which this was not because the mistake is too glaring to make honestly), and dishonesty (either in the form of lying about the world or about one’s qualifications).

The jury is still out on India about that point.  I will wait to see if I or CAGE can find a case where someone explicitly and quantitatively mis-reports the time trend.  Perhaps, notwithstanding the doubts I have about Indian government wisdom, such a technical error is less likely to happen.  After all, judging from the floods of impressive-seeming Indian applications to graduate school I have seen, there must be approximately one million people who have been educated in health statisticians in India.  (Interesting trivia:  That was at University of Texas.  At the University of Alberta School of Public Health we got very few applications from math-whiz Indians, who seemed to set their standards higher, and instead got floods of applications from unqualified Africans.)

So, though I had little more to add to what others had already written about these, there was a lesson that I will try to keep in mind:  Most newspaper readers, upon seeing the retraction of the ONS claim (if, hypothetically, they saw it), probably could not recognize that this was not some super-complicated mistake that a competent and honest group of researchers might occasionally make.  Therefore, it is important for those of us who recognize the difference – between subtle and possibly honest mistakes and the glaring dishonest ones – to point it out, and to not mince words about it.  Perhaps the credibility of political  factions who traffic in junk science would start to crumble if people could be shown how so many of the “little errors” they made were not mistakes that anyone could honestly make.

Unhealthful News 112 – New official guide to masturbatory fantasies

Ethicists Update List Of Acceptable Things To Masturbate To

Unveiling what may be the most comprehensive guide to socially responsible self-pleasure ever published, a group of leading ethicists released Monday its list of things that are acceptable to masturbate to.  The 2011 edition of the Standards and Values in Autoerotic Practices is the first revision in 17 years of the venerable reference used to determine what images and thoughts are appropriate stimuli for bringing oneself to orgasm.

Just to avoid any confusion, that story was from The Onion.  But as with most of their best satires, the humor is based on calling attention to something that is quite absurd, but that we usually let pass without notice.  No, I am not talking about masturbation.  Although…  …no, I don’t think I can pull off that kind of humor.  What I am talking about are committees that form to make a bright-line declaration about something that has no bright lines, sometimes self-appointed and sometimes appointed by officials who also have no particular claim on the matter.

The observation (from Moynihan) that everyone is entitled to his own opinion, but not his own facts, has gotten quite a lot of play in recent American political debates (Google finds almost 300 hits in blogs from this month).  It usually shows up in the context of criticizing right-wing economic plans that not only represent goals that most Americans do not support, but also are based on assumptions that defy both simple facts and economic theory.  That is, people who are exercising their right to their opinion about what society’s goals should be, generally an opinion that would be unpopular if they admitted to the details and all they imply, try to make up facts that make the implications of their goals more palatable, seem less costly, have miraculous benefits, etc.  A rather similar pattern can be found in some politicized areas of health science.  The most obvious are claims that public place smoking bans have miraculous health benefits; someone can believe that the bans are justified, but there is no justification for making scientifically nonsense claims (and if they feel those claims are necessary, it means they think that their opinion is not widely supported on its merits).

But the Onion story picks up on a different side of that truism:  Matters that are ultimately a matter of opinion cannot be turned into facts by convening a panel that gives us their opinions on the matter.  An expert panel certainly can help sort out scientific and technical ethical points, but ultimately their opinions that explicitly or implicitly use the word “should” are not facts.  So when a panel convenes to address whether we should maintain an aggressive military posture or whether e-cigarettes should be banned, or what is allowable when masturbating, it is possible that their opinions will be given the force of law, but they will never be facts.  (Note that this is separate from the question of whether such panels are good at answering purely scientific questions, which I will not address today.)

The Onion reports, “one of our top priorities this time was to eliminate all bias against homosexual impulses”.  This might be a subtle reference to the Diagnostic and Statistical Manual of Mental Disorders, the American Psychiatric Association’s pronouncement about what constitutes psychological illness, in which homosexuality was officially considered a mental illness as recently as the 1970s.  Was this a fact?  Obviously not.  Is it a fact now that homosexuality is not a disorder?  Well, no, actually.  It might be a fact that it is inborn and irreversible in most cases, but the question of whether it is something wrong is a matter of opinion, and is not up to the APA to decide.  Unfortunately, when society reaches a rough consensus on such matters the result is sometimes quite disturbing.  But that cannot mean that some group of scientists, medics, or philosophers can assume the right to form society’s opinion.  In the case the DSM and homosexuality, the changing of the official condemnation of homosexuality in 1974 lagged the enlightenment already shown by educated engaged members of society, and even by the government.

If it was at all controversial that,

 For the 23rd consecutive edition [of the Standards and Values in Autoerotic Practices], masturbating to a litter of newborn puppies is classified as “wrong, wrong, wrong.”,

then the declaration of the fictional ethicists would have no merit.  What makes the declaration reasonable (and funny) is how obvious it is.  However, it would be nice if the experts would offer some explanation as to why it is wrong (which might be the same as “why society thinks it is wrong”).  That was missing form the satire just as it is missing from most real Official Pronouncements.

Even ethicists, let alone psychiatrists or other physicians, have no special claim on what is ultimately good and right.  What they can offer is some insight into how to sort an analyze opinions.  So, to draw on extreme versions of the present example (might as well run with it), there is a tough question about the ethics of getting off from looking at a photograph of something such that (a) it would be unethical to take the photograph or distribute a photograph of (say, a surreptitious photo of someone through her window, though there are much worse example) or cause the event to happen, but (b) the ogler had nothing to do with any of those and just found the photo on the web.  This is akin the question of what to do with the medical knowledge the Nazis acquired by basically torturing innocent people to death.  There is a similar question about an image that pretends to be something unethical, like a photo of a young-looking 18-year-old woman posing to give the illusion that it is kiddie porn, or even just imagining the unethical with no intention of ever acting on it.  The ethicist can aid in sorting out these questions (e.g., to separate consequentialist points from symbolic issues) and there are also questions at the border of science and ethics that might be answerable (e.g., how the decision might create incentives for future behavior).  The value of that type of analysis should not be underestimated.  Unfortunately, when the panel’s opinion is reported in the news, it is simplistic and inappropriate conclusory statements that are reported, not useful analysis.

Consider a case of doing it right:  The FDA scientific advisory committee on tobacco formed an opinion about whether menthol in cigarettes causes disease.  Notwithstanding the criticisms of the committee for their political biases, they seem to have gotten the answer right.  But they annoyed some commentators by not stating their opinion about whether menthol should be banned.  However, they get credit for getting that bit right too.  After laying out the costs and benefits as best they could, their opinion about what to do would add no further information.  Perhaps they are a dozen of the ten thousand people in the world who have done the most intelligent, insightful, and educated thinking about the question, but they are certainly nothing more.

Additionally, the conclusions sections of research papers act quite similarly.  Insofar as the conclusions relate to interpreting the results themselves, they have a bit of value.  Just a bit though – I have a friend who has done lots of systematic reviews, and he told me he never once paid any attention at all to what the authors concluded that their results meant.  The authors’ opinion about what we should think about the world, let alone should do, is worth about as much as a Twitter post.  An analytic paper that argues or analyzes how to think about a normative question can come to legitimate conclusions about how the world is or what should be done.  But adding such a conclusion to the statistical analysis of one dataset provide no more backing or context than a tweet.  And yet it is that tweet that is typically featured in the news reports about the study, panel, or whatever.

The Onion story is funny because of all the popular human endeavors, masturbatory fantasies might be the one that is least vulnerable to control by Big Brother.  Even people in Saudi, Zimbabwe, or Bhutan can think about puppies if they really want to (though we can still hope that none of them actually do).  But the concept of having a panel deciding about allowable fantasies is remarkably similar to a committee deciding whether smoking or addiction is officially a disease, or how many weeks of gestation makes inducing abortion unethical, or whether there is such thing as autism spectrum disorder.  These can be legal questions, so some legal rule might be needed for practical purposes, but these are not factual questions, and so the right to have an opinion is not removed due to the pronouncement of an panel.  The panel’s opinion is no more immune to counter-argument than anyone else’s opinion, and obviously should never be cited as anything more than the opinion of a short list of fallible humans.

Finally, to end with a bit of a plot twist, I am going to offer a one paragraph argument that not everyone is really entitled to their own opinion.  Everyone gets a vote – that is a practical matter of law.  But if there actually is a body of scientific evidence and a careful analysis about how to think about the ethical aspects for some question, then you really should understand those before forming an opinion.  Failing that, you are not entitled to the opinion.  It is not ok to say “we should ban all public smoking” because you believe that passing exposure to second-hand smoke is substantially harmful (which would be a case of having your facts wrong) and because you have a vague notion that it endorses immoral behavior (though you have no idea what that even means and have never considered a careful analysis of the point).  You have the opinion, but it is not worth any more than your opinion about how to build a particle accelerator or the when humans first settled Hawaii, and your “entitlement” is rather shaky.  While you may have the legal right to espouse and even promote that opinion, you are on very shaky moral ground in doing so.

Unhealthful News 111 – Black markets are just markets

This is mostly background, with just a bit of news.  It is relevant to yesterday’s UN110 and an entry in our weekly reading list about THR, but did not really fit in either.

India recently banned the selling of “dip” products (sometimes incorrectly referred to as smokeless tobacco, but most of them are predominantly other plant matter, like betel nut, and other chemicals, rather than tobacco) in plastic pouches.  These single-serving products sold for the equivalent of a penny or two and seemed to be available on every block.  This odd new restriction could have been justified as a way to reduce litter, since those billions of little non-degradable wind-blown plastic pouches do make quite a mess.  But as I noted in UN64, proponents made it quite clear that this was a way to increase the cost of manufacturing and thus make these products too expensive for the “common people” (their phrase, not mine).  It is the Indian equivalent of location-specific smoking bans that supposedly have something to do with protecting nonsmokers, but are really just about making being a smoker less pleasant.

Like any supply-side intervention designed to reduce consumption, the plastic ban created a tension in the marketplace between the incentive to manufacture a desired product in the most efficient way, selling it for maximal profit in a free market, and obeying the rule.  The same principle actually applies to any regulation of a producer, such as pollution limits or rules against keeping employees chained to their work stations.  Purely from the perspective of making and consuming the good in question, it is more efficient for the manufacturer to ignore the rules.  The resulting efficiency gain from breaking the rules is split between the consumer (lower price) and producer (greater profit) in a proportion that is determined by some technical issues known as price elasticity, as well as whether others are obeying the rules.  I mention that last just to throw in an argument against those who suggest that producers decide how much profit they are going to make at consumers’ expense; it is more accurate to say they take the best they can get, which is based on forces beyond their control.

Anyway, the most efficient way to impose a supply-side intervention to lower consumption is taxes, but it is not the only way.  Anything that raises the cost of supply, such as requiring expensive packaging or periodically imprisoning people in the supply chain, has a similar effect on price and thus demand, but at a much higher social cost.  If you impose a tax, the price increase is an efficient transfer – that is, everything that the consumer loses the government gains – so there is no net loss to total social wealth.  Whereas if you raise real production costs then the extra price paid by consumers is just burned up in by the higher costs, lost to the world.  Or to put in terms that would be better understood by a government official, taxes not only raise the price, but provide more money for the government, so are win-win (assuming raising the price really is a win, of course).

So why a ban on plastic packages?  Presumably the brains(?) behind the plastic package ban must have decided that imposing an equivalent tax would not work because the Indian government was not functional enough to enforce collection.  So, the fact that they chose to forgo taxation suggests they did not think they could enforce it, due to inefficiency, corruption, etc.  In some sense it is a clever solution:  It is quite difficult to figure out if taxes have been paid on a particular unit of product or if they are being collected at point of sale, but very easy to see if the cheaper plastic is being used.

But if that is the explanation, why, oh why, did they think that they could prevent some kind of black market from emerging?

Alternative markets are ways of taking advantage of the aforementioned tension and gap between the efficiency of unregulated competitive market and obeying all the rules.  The bigger the tension/gap, the more profitable and successful will be the black market in the absence of really intense enforcement efforts.  So since cannabis cannot be sold in stores, alternative supply chains spring up, with the higher-than-free-market prices reflecting the cost of occasionally being arrested or shot at, though the fact that prices are remarkably low means that enforcement is pretty ineffective.  High cigarette taxes create a enough of a gap between the free market and paying full price that there is room for both profit for the smugglers/counterfeiters and lower prices for consumers even though the illegal supply chain is much less efficient than those of the major legal manufacturers.  And even something as unexciting as taking Coke out of the vending machines in the city office buildings in Boston will inevitably result in some bored cubicle workers supplementing their income and helping out their neighbors by bringing in a cooler full to sell every day.

Anyway, my motivation for writing this explanation of markets in the face of prohibitions and partial prohibitions was just to give an excuse to quote this passage from The Times of India about how, sure enough, a black market in plastic packaged dip appeared almost immediately:

MUMBAI: The racket, involving the smuggling of gutka pouches into Maharashtra from neighbouring states like Gujarat to be sold here at thrice the actual price [emphasis added], continues unabated in the thriving black market.  The blackmarketeers are making huge profits by selling the banned gutka and pan masala sachets by charging three times the actual prices. One popular brand of gutka, whose MRP is Rs 4, is being sold for Rs 13, and another brand, whose MRP is Rs 7, is sold for Rs 20.

The rather vital fact that the reporter seems to not understand is that the actual price of something is whatever it is sold and bought for.  (Am I the only one who laughed out loud at that?  I am a bit afraid that I might have been.)  Yes, obviously we can just substitute “MSRP” or the “former price” for what he called actual price.  But I think there is more to this misunderstanding than mere incorrect wording in the national paper of record.  Factions in India keep talking about expanding the plastic ban to a complete ban on the products, thinking that would work out well.  But this story demonstrates that consumers are willing to pay at least triple the competitive market price for the product and, in a country with a lot of under-employed labor, that is undoubtedly enough of a gap to support a very nice black market.  A government that decided that it could not enforce a tax increase seems unlikely to be able to stop it.

There is nothing exotic or remarkable about this.  If those who have control over a market supply a lousy product or charge too much for it, or refuse to supply it at all, someone will step in.  That is the story of the market that gives us e-cigarettes (because pharma companies refused to produce a good cheap nicotine product), Firefox (because Internet Explorer was so lame), and crystal meth (because importing cocaine was made difficult).  You really have to wonder if the Indian government thinks it can succeed where Glaxo, McNeil, Microsoft, and the U.S. government failed.

[Coda: The examples in the last paragraph were chosen because they were cases where the previous products were creating huge fortunes while the entrepreneurs offering the alternatives have done ok, but have mostly earned only a workaday modest living through their efforts.  Market innovations like these often create a lot more surplus for consumer than for producers, Facebook and the question of whether meth is really good for anyone notwithstanding.]