How to use misleading statistics in a bid for government funding - the LGA and public health at their finest

Terrible:

Council chiefs have warned of a ‘childhood obesity crisis’ as new figures reveal that the number of young people being treated for Type 2 diabetes has increased by nearly 50% in five years.

Not the statistic but the spectacularly misleading way in which this scary paragraph is framed. It is, I'm afraid, an absolute classic of the public health scare story genre - guaranteed to get media coverage but utterly deceptive.

So let's look at the numbers:

Figures from the Royal College of Paediatrics and Child Health show that 745 children and young people under the age of 25 received care for Type 2 diabetes in Paediatric Diabetes Units in England and Wales in 2017/18.

The first point here is that we're not talking about children here - unless we've begun categorising those aged 18-25 as children? Of the cohort in question (under 25 years old), a third -32% to be more precise - are adults i.e. aged over 18. Some of them may be obese and may have Type-2 diabetes but using these figures to claim an increase in child diabetes is simply wrong.

And that cohort? There are 17.4 million of them meaning that the 745 who have 'received care' for Type-2 diabetes represent a massive 0.004% of the population. There may have been an increase since 2015 of 50% but this is still not in any respect a crisis (except perhaps for the individuals most of whom will be over 18). Even with the more inflated Diabetes Association estimate of 7,000 under 25s who have received support for 'diabetes-related' conditions, the problem still only affects 0.04% of the cohort.

There has been a trend in public health using secondary factors to substantiate proposals for either new regulations, new taxes or more local government funding. Mostly this is because there's not really any evidence that child obesity is rising:





That's from King's College - here's the latest from the NHS itself:



Again no indication that child obesity is rising (indeed it has fallen for children arriving in primary school). So public health look for other statistics to peddle their hysterical fussbucketry, most commonly statistics like these on Type-2 diabetes that, while interesting, suffer from a whole load of flaws (changes in referral practice, greater awareness of symptoms, new centres and facilities to support diabetes) that mean the increase could be entirely unrelated to changes in the number of obese children and relate more closely to better diagnosis and more provision in the NHS system - both good things but no justification for advertising bans or bunging millions for local councils to splurge on useless obesity programmes.

....

Statistics are altogether too bourgeois for the public sector elite

I've been thinking for a while about Graeme Archer's article on how 'getting' statistics is as important as 'getting' Shakespeare yet people still, in that giggling way, exclaim how they were never any good at maths.

There is no “either/or” between words and numbers; at the same time, of course, there is. CP Snow’s two cultures exist, most clearly in the words/numbers dichotomy, but only because we structure them into existence through conscious decisions about how to educate our young. It’s a human choice, not a law of the universe. Good with words or good with numbers is a story we tell about ourselves, and like all stories it has its heroes, and villains.

Now I'm a social scientist (if I'm anything properly academic) who once gloried in the title of Research and Planning Director and I recall a number - see what I did there - of stories about folk dumbfounded by maths and stats. We once prepared an analysis of customer geography for a knitting wool company (sexy, eh!) based on a simple index and had to spend the first twenty minutes of the presentation explaining what indices were. And when I did my 'Research Methods' module for my MSc, we were told to avoid quantitative research because (I summarise) maths is hard and you don't need to do it.

Such is the reality of a world where my personal experience of buying a railway ticket is a better guide to policy than statistics explaining why I am an outlier in buying such an expensive ticket. Or where - as I put it in a debate at last year's Battle of Ideas:

We’d reckon on uplift in response of around 2X or maybe 3X compared to a random selection. Great until you realise that the response to random was around 0.2% - all that clever technology means that, instead of getting ignored by 998 out of 1000 people, you only get ignored by 994.

Only the 2X or 3X gets reported not the actual numbers even though they tell us we needn't fret so much.

Statistics matter yet the extent to which we understand them or appreciate them is troubling. I recall being told - in very definite terms - that my comments on the relative poverty line were wrong because I was using the median household income not the mean and "median isn't an average". This is despite the fact that median is the right measure where there's a lower bound (i.e. you can't have a negative household income - which might come as a surprise to bankrupts).

The thing with Graeme's article, however, is not that people don't know enough maths and statistics but that they are proud of this fact. And, you know, I might have just found a little glimpse at the reasons why this is the case - numbers, counting, accounting are terribly bourgeois things. Here's a chunk from a chapter in Deirdre McCloskey's Bourgeois Equality (the chapter is entitled 'Aristocrats Scorned Measurement'):

In England before its bourgeois time Roman numerals prevailed. Shakespeare's opening chorus in Henry V...apologises for showing battles without Cecil B. DeMillean numbers of extras: yet "a crooked figure may/ Attest in little place a million/ And let us, ciphers to this great accompt, / On your imaginary forces work." The crooked figure he has in mind is not Arabic "1,000,000" but merely a scrawled Roman M with a bar over it to signify "multiplied by 1,000": 1,000 times 1,000 is a million.

McCloskey - like Graeme Archer - quotes Samuel Johnson (albeit a different reference):

"To count is a modern practice, the ancient method was to guess; and when numbers are guessed they are always magnified."

And that modernity was, in Johnson's time, the advent of Bourgeois England - Capitalist England (although McCloskey would be cross at the sloppiness of this latter designation). Before this time, accounting was a grubby thing of merchants, pursers and bursers not something the great and good should be bothered with. Indeed, McCloskey goes on to note that, prior to 1803, students arriving at Yale were expected to be fluent in Latin and Greek but not to be qualified in arithmetic. Such mundane things as statistics were beneath such grand folk.

We appear to have come full circle with quoting poetry and qualitative (for which, usually, read anecdotal) analysis given greater credence than any sort of proper measurement, analysis and appraisal based on statistics, probabilities and other scary number-crunching things. As Simon Jenkins disdainfully put it (when it seemed his basic statistical knowledge was found wanting):

I seriously doubt this poll, since it implies that two-thirds did know the answers. All on whom I tested it failed, including myself. Nor could they see the point. With one voice they replied: “That’s the sort of thing you learned at school.” So what is the point?

What were the sorts of question? Calculating the mean, median and mode - terms used every day in the Guardian where Jenkins writes. The area of a circle. And even long division and multiplication. Not even GCSE maths, not much advanced on what we'd like an eleven year old to know. We don't need to know this stuff, say the bookish elite, it's smelly maths.

Yet how can you know whether government policies - reducing poverty, improving health and so forth - are effective if you've no idea how the things we're reducing or improving are measured? I'll tell you how - we use anecdote, stories. So, rather than look at the statistics we relate the tale of someone's grandma or how a single mum is struggling on benefits. We sometimes gather together several of such stories and embellish them with commentary from 'experts' relating their own understanding based on further anecdote - or 'qualitative research' as they like to call it.

Statistics, maths, measurement, accounting, calculation - these are the tools of the capitalist, the merchant, the city trader. Thing to be disdained and dismissed in favour of our, often pre-judged, opinion founded on at best a reasoned assessment but more commonly on a collection of tales. We might then hold our noses and wander into the world of maths seeking out some numbers that seem to match what we've found from our tales. People compare apples with pears, use percentages when the numbers are too small for this to make sense, and calculate means when the bounds make the mean meaningless. Journalists - often with the title Science Editor or Health Correspondent - present headlines that bear no relationship to the research they report on. Not because they want to mislead but because they've no idea what 'statistical significance' means let alone what a p value is.

Hardly a day passes without us witnessing people in powerful and influential positions dismissing the evidence of statistics in favour of anecdote and conjecture. And, so long as people can respond by quoting Disraeli - lies, damned lies and statistics - without being laughed at, there is little chance that we'll see the proper use of measurement in the formulation of public policy. Meanwhile, out in the world of markets, capitalism, trade and investment, people have no choice but to use measurement and statistics, without them they would fail. For the public sector elite, however, such concerns are just too bourgeois and instead they make policy inspired by stories in the Guardian or Daily Mail.

.....

The electoral register is the most accurate source for adult population data

Right now the electoral registers are probably the most accurate estimate of the UK's adult population. There are two reasons for this - one a credit to the Coalition government and the other to the insistence on data sharing by local authority chief executives. What disappoints me is that opposition parties at Westminster continue to present the idea that there is somehow a better estimation of adult population available for the drawing of constituency boundaries.

Let's look firstly at the the new electoral registers based on a process of individual registration.This new system was introduced for various reasons including the persistence of register stuffing (that is registering people to an address who aren't living there or in some cases don't even exist), inaccuracies such as dead and gone way folk (nixies as we call then in direct marketing) staying on the register, and a whole load of people who for various reasons weren't registered at all.

Had we just stuck with introducing a system of individual registration then it is beyond doubt that the numbers registered would have fallen and that fall would have disproportionately been among the young and the poor. But the new system didn't take that approach but instead allowed existing verified name and address data within government systems to be shared for the purpose of registration. As a result somewhere between 65% and 80% of registrations were concluded using existing information and this information, given much of it was for benefits recipients, disproportionately focused on the poor. Anyone receiving a benefit is automatically registered - that's every mum, all the registered unemployed, those receiving in-work benefits, retired people and those receiving sickness or ill health support.

We can add to this the use of council tax records, the DVLA database, MoD staff records and some higher education records. All-in-all a pretty comprehensive effort to ensure that most of the registration process didn't require expensive and time-consuming paperwork. To fill the gap, local authorities undertook a variety of different approaches including traditional mailshots, door drops, advertising campaigns and canvassing. The result is a system of registration that is over 90% accurate even before the addition of a further 2 million electors - an extra 4% on the total - during the first half of 2016 (controversially excluded from the drawing of new boundaries).

On the basis of this successful (but still not perfect) system it seems sensible to use the electoral registers as the basis for drawing up boundaries for parliamentary constituencies. Some seem to differ, arguing that we should use the "whole adult population" as the measure. The basis for drawing boundaries using a 'whole population' measure has to be the 2011 census and this is already five years out-of-date. We should also note that the census is not itself a precise identification of every person (although it strives to do this) and the data is adjusted to account for under-reporting in some areas and this data was challenged by some local authorities. Again, the census is better than 95% accurate which is good enough for most purposes but in this it isn't much better - at the point of collection - than electoral registration. Its advantage isn't a better identification of individuals at addresses but rather the richer data associated with the individuals actually identified.

And this is all out-of-date so we would need to make some adjustments to the numbers so as to be accurate. At the national level this is pretty straightforward - add and subtract births and deaths then adjust for net migration to get a pretty accurate estimate. For local authorities the first part (births and deaths) is easy but migration isn't as we've no requirement - such as is the case in Spain - for registering residency. We'd have to use proxy measures such as the council tax base, the Post Office change of address file and (irony) the electoral register. And this would still only get us a measure at the local authority level rather than the ward level data needed to draw up boundaries. None of this makes for a more accurate estimation of ward-level population than the electoral register.

There's a valid criticism arguing that those 2 million 2016 registrations should be included in the review but the effect of this would be pretty marginal unless the distribution of that 2 million is very skewed in terms of geography. It's effect would be to shift the quota range from 71-78,500 to 73.6-81,300 a result likely to further disadvantage smaller inner city seats - there's no evidence that excluding these voters would have anything other than a very marginal impact on the new seat distribution.

As a last thought, we can note that the last full review of English local council ward boundaries (2003) was on the basis of a future population projection rather than the census or electoral register. It is clear that, for many places, this was a pretty unsatisfactory measure - you only need to look at the population change in Leeds Council's Headingley ward to recognise that current population is a better basis for boundaries. And right now the most accurate source of current adult population numbers at ward level is the electoral register.

...

"The bigger the number the better" - public health campaigners' cavalier attitude to evidence

An entirely gratuitous picture of cake

I've felt for a long time that single issue campaigners of various kinds - poverty, public health and so forth - have a tendency to choose statistics that maximise the scale of the problem they are campaigning about. From the perspective of campaigning as a business, this makes a lot of sense - if we can demonstrate there are huge numbers 'living in poverty' or some sort of booze or food related crisis then the need for our campaign is all the greater. And we can present the stats to compliant - and media-scared - governments who will carry on providing the funds to pay us so we can carry on campaigning.

This hyping up of a problem does however have a downside - by making the numbers ever larger and the problem greater and greater we feed scepticism and cynicism in the population. If your recommended alcohol limits boil down to a glass of dry sherry twice a week the drinking public (and that's most of us) are going to think something like "that probably a load of nonsense, isn't it", And that public will carry on behaving just as they were before.

So the campaign is sustained because government is given scary figures by the campaigners. And the unwillingness of the population to change its behaviour (because it doesn't believe those scary figures) further reinforces the view of campaigners that "something must be done".

And now we have some evidence to support this theory:

People who think they are overweight or obese are more likely to pile on the pounds than those who are unaware that they may be heavier than doctors would advise, according to research.

The researchers show that telling people that they are fat is unlikely to work because of the stress associated with the stigma of fatness. Yet the obesity industry is utterly predicated on two interpretations of statistics - firstly the conflating of 'overweight and obese' into on number and secondly the narrowing of the definition of 'normal' weight. We're repeatedly told that two thirds of more of adults are 'overweight or obese' and in doing so extend the stigma of being a bit chubby from body image alone to body image plus health. This is despite there being no evidence at all showing that being overweight is unhealthy.

"Our results are similar to those from other recent studies, confirming that underweight and obesity class II+ (BMI > 35) are clear risk factors for mortality, and showing that when compared to the acceptable BMI category, overweight appears to be protective against mortality."

This is a pretty consistent finding - far from being chubby shortening our lives, the reality is that is probably extends them. If we were - given what the evidence tells us - to redefine healthy and unhealthy weights so as to direct appropriate interventions, a better definition would focus 'obesity' on people with a BMI in excess of 35. But were we to do this the numbers might fall from 'two thirds of adults and a third of children' to '5% of adults and 1% of children' - still a lot of people but not exactly a crisis. Such a change would challenge the huge sums being spent on anti-obesity campaigns and would call into question the ongoing campaigns against sugar, fat and the working class diet.

I am repeatedly told by public health folk that their work is 'evidence-based'. And they are very quick to point out studies that support their position. But when the evidence - as we see here with obesity - challenges the preferred position (and funding - Bradford spends over £2 million on its obesity team) it is simply ignored. By not fitting the narrative - 'global obesity crisis' - the pesky evidence undermines the strategies of public health and brings into question its programmes of work. This cannot be allowed.

....

All-population approaches don't work - even for national security

****

We are familiar with the use of all-population strategies to respond to public health challenges - smoking, drinking, eating too much and so forth. The argument is essentially that, if sufficient people are engaged in a negative activity, then it is worthwhile targeting the whole population - thus we impose high duty rates on alcohol, people call for sugar or soda taxes and we impose constraints on the supply of the product (up to and including a total ban).

The problem is illustrated by the success of such a strategy in the UK's consumption of alcohol - this has fallen by around a fifth over the past decade as a result of much higher duty rates, extensive education measures and high profile campaigns from all public agencies targeting binge drinking. So the strategy is a success? Seems not to be so because, assuming that the main gain is a health gain, then the strategy has failed:

The number of hospital admissions for alcohol related harm increased by 47%—representing an increase of more than 800 each day—over the five years between 2004 and 2009, show latest figures for England.

Put simply we saw a continuing rise in ill-health related to alcohol during a period when overall alcohol consumption was falling. The all-population approach had failed (at least in terms of health outcomes - it seems to have been effective in terms of crime). This same problem is repeated when we look at other issues - overall calorie consumption and broad measures of obesity are static or falling but we are seeing rises in chronic conditions related to obesity.

So it should come as no surprise to discover people questioning all-population strategies in other areas of policy:

Surveillance of the entire population, the vast majority of whom are innocent, leads to the diversion of limited intelligence resources in pursuit of huge numbers of false leads. Terrorists are comparatively rare, so finding one is a needle in a haystack problem. You don't make it easier by throwing more needleless hay on the stack.

We cannot us lots of computer power to scan and analyse billions of data rather to replace the dull job of gathering intelligence, targeting known or likely suspects and then conducting specific surveillance. Just as with health - where we should target resources towards those who actually have a problem - the growing security infrastructure really has little impact in the prevention of terrorism or crime.

The problem is that, just as blanket restrictions of booze or boozing appeals to a certain sort, the introduction of all-population surveillance provides a comfort blanket for a nervous population. Confiscating nail clippers and half empty water bottles from tourists boarding a flight to Malaga at a regional airport contributes nothing to the fight against terrorism or organised crime but does give the impression that the authorities are deeply concern (and doing something) about these problems.

It cheers me (although does not explain why government persists with all-population measures) that there's a mathematical explanation as to why mass surveillance is a lousy way to fight terrorism.

No matter how sophisticated and super-duper are NSA’s methods for identifying terrorists, no matter how big and fast are NSA’s computers, NSA’s accuracy rate will never be 100% and their misidentification rate will never be 0%. That fact, plus the extremely low base-rate for terrorists, means it is logically impossible for mass surveillance to be an effective way to find terrorists.

And if it is true for terrorists then it is true for anything where the proportion of the population we need to target is small. Or so it seems, at least to someone who has only a basic understanding of Bayes' Theorem. So answer should be to deal with the actual problem rather than bother at the whole population in the vain hope that this will work. It seems it won't.

....

Misinformation, ignorance and prejudice masquerade as a serious article about obesity.

****

A friend of mine at university once described articles written by the likes of Enoch Powell or Tony Benn as superficially works of logical completeness and coherence that, on closer examination, reveals a huge leap of what can only be faith half way through the article.

This article on obesity lacks the intelligence, wit or wisdom of Enoch or Tony but it suffers the same problem. It starts like this:

McDonald’s cookies have an energy density comparable to hydrazine. Hydrazine is a rocket fuel used to manoeuvre spacecraft in orbit. It was astonishing, then, to watch a small child graze through two boxes of the desiccated biscuits in one sitting. His parents watched on, preoccupied with their own colossal meals: a noxious amalgam of meat, grease and sugar.

Now I'm not about to defend the quality of McDonald's food (although - and we'll return to this - there isn't any proven link between fast food and obesity) but we know where the author is coming from. We have a problem with obesity and, our author argues, it isn't enough to say that it's a matter of personal choice.

It's an argument - one I don't agree with but an argument nevertheless. And we do have a problem with obesity. However, the author loses me with this single line:

Over 63% of Australian adults are overweight or obese.

Note what has been done here. We were talking about obesity - being grossly and unhealthily overweight - and suggesting that perhaps the morbidly fat really do have a problem resisting food. But now all of a sudden we're talking about obese and overweight. We have, to use that piece of sociological jargon, 'problematised' being overweight by implying that it falls in to the same health category as being obese.

And, to put it bluntly, this simply isn't true. Here's the science:

Relative to normal weight, both obesity (all grades) and grades 2 and 3 obesity were associated with significantly higher all-cause mortality. Grade 1 obesity overall was not associated with higher mortality, and overweight was associated with significantly lower all-cause mortality.

This is not some little study either but:

...97 studies were retained for analysis, providing a combined sample size of more than 2.88 million individuals and more than 270,000 deaths.

Essentially the research is saying that having a BMI of between 25 and 35 doesn't represent a health problem  - overwhelmingly the people our author is talking about fall into this category.

So what is the actual scale of the problem? If we take morbid obesity as the essential measure (in the UK this is defined as a BMI over 40) then currently around 1.5% of men and 3.5% of women are morbidly obese. Now this is a lot of people - about 1.5 million - so we shouldn't ignore it as a problem but it isn't anything approach the scary 63% that our author cites. Even if we add those with a BMI between 35 and 40 the numbers only rise to 5% or so - between 3 and 4 million.

And this brings us back to fast food. Quite simply there isn't a strong connection between takeaways and obesity (which isn't to say that fat people don't eat in McDonald's but to say that's not why they're fat):

When the researchers weighed these children they found something rather interesting. Here are the average body mass index (BMI) figures for each group by frequency of visits to fast food outlets. Bear in mind that a 'healthy weight is 18.5 to 25:

Weekly visits        BMI

Every day:            17.8

4-6 times:              18.3

2-3 times:              19.6

Once:                    20.3

Less than once:     21.4

OK this is for children but it makes the point - quite remarkably showing a negative relationship between regular fast food consumption and obesity. It's whats in the fridge at home and the drawer in the office that's the problem not Burger King or the kebab shop.

Our author concludes that we are all victims of:

...the roots of overconsumption: cost of living, manipulative marketing, nutritional misinformation and – often overlooked – simple palatability.

The overconsumption point is an interesting one for, as our author should know but doesn't, overall calorie consumption has been falling. We're still fatter but it's too simple to blame advertising, fast food, offers of chocolate oranges or Big Sugar for the problem. A proper assessment would pick up these facts and ask questions about our sedentary lifestyle, about the support given to very fat people and medical interventions that are possible.

Instead Ben Brooks (an arts/law student or so his biography tells us) chooses to play silly games with the statistics - the evidence, the truth, if you prefer - in order to make his snide little prejudice against McDonalds into a public health point.

Update: some more practical evidence that it's not McDonald's but our broader food choices that matter are on view in this fascinating student project.

...

Scroungers?

****

Such is the rhetoric I believe - we are asked to believe that either there are loads of people sitting on sofas, smoking, drinking cheap lager and eating sweets while defiantly refusing to work, or else that eager, smart and enthusiatic folk are valiently (and vainly) struggling to find work.

And every now and then we get a little insight:

Scrutinising the period from July 2012 to June 2013, the Labour Force survey found that 65 per cent of people across Bradford were in some form of employment, but 20 per cent, or a fifth of those questioned, were classed as “economically inactive” and “not wanting a job”.

This group chose not to disclose a reason why they did not want to work, ignoring options such as being on long-term sickness, looking after a family home or being a student. 

So this group - about 70,000 people - aren't looking for work, aren't raising a family and aren't ill. Are they our much debated 'scroungers' living off benefits, occasional cash-in-hand jobs and petty crime? Or is it even more complicated than we're told?

It could be that there are problems with the survey - although one hopes that the Office for National Statisitcs (ONS) knows a thing or two about this and is likely to get it right. Perhaps some of these people have literacy or comprehension problems making the findings unreliable. Or there really are a lot of people in Bradford who aren't working, aren't caring and aren't ill but aren't looking for work. Doubtless they are the drone-like scions of Bradford's millionaire class!

Even if only a proportion of this group are actually lounging around doing sod all on benefits it says a great deal - about the system, about education and about how tolerant we are as a society. I think of other people who're turning the heating down a notch this winter, cutting back on life's little pleasures, perhaps forgoing a holiday. In part so their taxes can pay for people who have no intention of getting any work.

There is, perhaps, a limit to tolerance?

....

"Microlives": I'm pretty certain this is utter tripe...

****

...from the Guardian (where else) with some people's wonderful new 'live forever' theory:

The Norm Chronicles, a new book by journalist Michael Blastland and Professor David Spiegelhalter that has a neat idea which turns all these abstract dangers into a concrete figure.

It centres on this idea: once you hit adulthood (or, being more precise, 22 for a man and 26 for a woman) you can expect to live for around 500,000 more hours – or a million half-hours. Each of those 30 minutes of life is a "microlife".

By working out the average effect of, say, smoking or eating red meat, we can figure out a cost in microlives for different habits. A portion of red meat, for example, costs you a microlife – in the words of Blastland, it's "a 30-minute chip off your stock of adult life".

This seems to me to be ignorance squared - taking averages (I guess 'norms') and using them as a predictor of individual life expectancy is not either good maths or good science. Maybe that's not what the book says - the good professor is, after all, a statistician. But it is what the Guardian says the book says - essentially that we can quantify the effect on our individual health of actions where the effect is based on estimates of how much the action adds or subtracts from our lifespan.

The problem is - and if we thought about it for a second we'd know this - that the estimates are open to question. We really haven't much of a clue about the impact of eating red meat on life expectancy even if we do have a general (if challenged) idea that a diet of red meat isn't ever so healthy. For sure, where there's a known dose-response effect (e.g. with smoking - note the word is smoking not tobacco - or alcohol) there's perhaps a bit of a case. But for things such as exercise there is little evidence that getting sweaty on the treadmill extends life - the the adding of microlives on the rowing machine is probably nonsense.

What we have here is extending the general to the specific (from the whole population average to little old me or you) combined with evidence that, to put it mildly, is open to question and perhaps not epidemiologically sound.

But I guess that the gullible Guardianistas are looking for a 'Spirit Level' for personal health and these authors have delivered! However, such tripe is best served with onions and accompanied by a good claret.

....

About that underage drinking...

****

Yesterday "The Doctors" were in full cry about alcohol and "the children":

Sir Ian Gilmore, the AHA's chair, said action was especially urgent given that UK teenagers drink much more than the European average.

Well it may be 'much more' (although, like the £55 billion 'cost to society' of alcohol, this is unevidenced and probably untrue) but it isn't very much:

Regular alcohol consumption by 11 to 15 year olds has fallen by two-thirds in the last decade - from 20% to 7% - and the proportion of these children who had ever drunk alcohol fell from 61% to 45% in the same period.

As always - and it should worry us - "The Doctors" just make stuff up about health risks knowing that reporters who stopped any studying of science at 14 will simply believe everything they're told.

Quite simply, we really don't have the problem with booze that prohibitionists and temperance campaigners like Sir Ian Gilmore would have you believe.

...

How to lie with statistics - asthma special

****

Today the BBC - and assorted other nannying fussbuckets - have been slavering over a report that claims to show how the smoking ban resulted in a massive drop in children admitted to hospital with asthma:

There was a sharp fall in the number of children admitted to hospital with severe asthma after smoke-free legislation was introduced in England, say researchers. 

A study showed a 12% drop in the first year after the law to stop smoking in enclosed public places came into force.

They are using statisitics (this is perhaps spelled L-Y-I-N-G):

Yes folks, that's their evidence - evidence that contradicts what Asthma UK say about the problem:

Asthma UK said the number of emergency admissions had remained unchanged for a decade 

(Yes folks, the BBC reported that)

One day a BBC journalist will actually do his or her job and ask some questions, poke a bit at the evidence - anything other than simply reprinting the lies contained in the nannying fussbuckets' press release.

...

Eating stuff doesn't cause cancer....

Pie. A very good pie. From Ellisons in Cullingworth

Over recent years assorted nannying fussbuckets and attention seeking "researchers" have bombarded us with tales that warn how those wonderful foods we love are giving us cancer. Not that I was taking any notice but it does seem that it was - to be polite - a little exaggerated. At least according to some American academics:

...US scientists have warned that many reports connecting familiar ingredients with increased cancer risk have little statistical significance and should be treated with caution.

"When we examined the reports, we found many had borderline or no statistical significance," said Dr Jonathan Schoenfeld of the Harvard School of Public Health in Boston.

In a paper in the American Journal of Clinical Nutrition, Schoenfeld and his co-author, John Ioannidis of Stanford University, say trials have repeatedly failed to find effects for observational studies which had initially linked various foods to cancer.

These foods included:

...flour, coffee, butter, olives, sugar, bread and salt, as well as peas, duck, tomatoes, lemon, onion, celery, carrot, parsley and lamb, together with more unusual ingredients, including lobster, tripe, veal, mace, cinnamon and mustard.

Plus, of course, as the Daily Mirror puts it - the "British breakfast":

A health warning on the British ­breakfast was lifted yesterday after scientists ruled that bacon, tea and burnt toast may not cause cancer after all.

After months of stories linking the ­nation’s favourite foods with the disease, US scientists now say there is in fact NO evidence that they are harmful.

What on earth will the Daily Mail publish now?

....

Police, crime and public honesty - a statistical lesson

****

It is pretty clear that rates of crime don’t correspond to any of things we’re always calling for – more coppers (on the beat of course), tougher sentencing, bigger prisons, capital punishment or flogging in the public square.

Recorded crime...fell by 4%, continuing the long downward trend in crime since 1995, and dropping below 4m offences for the first time in 23 years.

The Office for National Statistics (ONS) said violent crime had fallen by 7%, including a 2% fall in robberies.

We’d also been told – mostly by chief constables protecting their empires – that reductions in police spending during a recession would result in a surge of crime:

Acting Chief Constable Chris Weigh of the Lancashire force said the loss of front line officers had resulted in an “inevitable” increase in the number of offences being committed.

Seems this top copper was wrong! The real problem is that – because we’ve focused on police, punishment, prisons and probation – we don’t really understand why crime has fallen so rapidly over the past 20 years. Or indeed whether it will continue to fall. What we will be able to say is that the overall funding of policing and economic recession does not lead to more crime.

So what are those factors? Well it seems that simple economics is a factor – stealing stuff is harder and selling it on is more difficult (as well as less lucrative). So professional thieves have shifted to other crimes:

...with significant rises recorded in the last two years in metal thefts triggered by soaring commodity prices

While the opportunist has taken to nicking bikes and lawnmowers from sheds.

However, the truth may be that we’re really a lot more honest than the authorities give us credit:

Mobile phones deliberately left in pubs and clubs by Sussex Police to catch thieves were all returned.
 

Officers planted phones fitted with tracking devices in nine clubs and pubs in Hastings and St Leonards as part of Operation Mobli on Saturday night.
 

However the phones were handed in at the bar or security staff and not one was stolen.

...

So are we getting fatter or not?

****

I suppose it couldn't go unexamined - I remain convinced that obesity is less of a problem than some would claim. And I also feel that the most up-to-date health statistics support my argument.

Let's start with this graph from "Adult anthropometric measures,overweight and obesity" published by the NHS:

As I've pointed out before there was a significant increase in levels of obesity but this appears to have come to an end (although evidence of any fall in adult obesity is limited). The commentary with this graph says:

The rate of increase in obesity prevalence has been slower in the second half of the period than the first half, and there are indications that the trend may have been flattening out in recent years. However, obesity in men and women in 2010 was at its highest level since 1993, and in men the 2010 level was also significantly higher than in the period between 2000 and 2005.

We could note also (which the commentary doesn't) that the levelling off in rates of obesity matches a methodological change - allowing for non-response. However, the essential point in all this remains that obesity levels are not rising but appear to be on a level trend. This may not be desirable in overall public health terms but it does not constitute and actual or looming crisis.

More importantly the problem does not seem - as the "let's scare everyone about sugar" brigade want us to believe - to be linked to overall diet. After all, if this were the case we would expect significant increases in levels of 'overweight'. However the same report says this:

Among men and women, the proportion who were overweight (BMI 25 to less than 30kg/m2) has changed very little between 1993 and 2010, fluctuating between 41% and 47% in men and between 31% and 34% in women.

 The point here is that the obesity problem is a matter of behaviour - people eating too much of the wrong sort of food - rather than a consequence of industrial food production methods.

....

Lies, damned lies and alcohol statisitcs (revisited)

The National Health Service Information Centre (NHS IC) has released its latest report on alcohol statistics. As ever Nigel Hawkes of Straight Statistics is on hand to try and help us with comprehension. However, even Nigel is confused:

The bottom line is that the NHS IC admits that its old method of measuring admissions attributable to alcohol exaggerated the increase since 2002-03 because it failed to take account of changes in hospital coding practice.

So that's clear. Except:
  

...it still publishes a table (4.2) based on the old, discredited calculations, as well as another table (4.11) that takes account of the adjustment. Which are we supposed to believe?  According to Table 4.2, total alcohol-related admissions rose between 2009-10 and 2010-11 from 1,056,900 to 1,168,300. But according to the adjusted measure in Table 4.11, they fell over the same period from 1,208,100 to 1,168,300.

Right, alcohol-related admissions have either risen or fallen over the last year. This is very helpful.

Nigel thinks that the measures are all a lot of toss (he actually says "unfit for purpose, adjusted or unadjusted") but this won't stop the usual collection of nannying fussbuckets from making the most of the figures. And guess which figures those folk will use?

There is a serious problem with NHS coding (and not just for alcohol-related conditions) - it relies on turning complex conditions into answers to a check list and is open to manipulation both at the point of collection and subsequently. Yet we are making huge decisions about health priorities on the basis of this sort of dubious, unreliable data.


....

Obesity rates are falling not rising - so why must doctors lie about this?

****

We've got rather used to the various clubs of doctors - BMA, RCS and suchlike - telling us that alcohol consumption is rising when it isn't (even the BBC now recognise that it is for heaven's sake). Now these New Puritan institutions are lying about obesity:

According to the latest research, 48% of men and 43% of women in the UK will be obese by 2030, a trend that will significantly increase the prevalence of strokes, heart disease and cancer, and lead to higher costs for the NHS.

Now unfortunately, the Guardian doesn't link to that latest research. However, the latest actual statistics from the Office of National Statistics tell us that rates of obesity are falling:

Despite the government ignoring the anti-obesity lobby's urgent suggestions for traffic light labelling on food and suchlike, the latest figures show that obesity amongst men has fallen to 22% and the female obesity rate has fallen to 24%.

So something must have changed - either the Academy of Medical Royal Colleges are scandalously misinformed or else the British public has been on a massive eating binge in the last year (those latest figures are from 2011).

Ah but what about the children say the doctors:

Charlie Powell, campaigns director of the Children's Food Campaign, applauded the academy's intervention. He said: "Andrew Lansley should act on this excellent set of robust recommendations, but his track record suggests that he will once again ignore the advice of our best medical experts."

Ah yes those children - I don't have figures for everywhere but I'm pretty sure Bradford won't be out of the ordinary in terms of obese children -  here, for Year 6 children, there has been a slight fall over the past three years and the rate remains below 20% (marginally above the national average). And note that this uses the very discredited measure of Body Mass Index.

None of these actual facts supports the argument of the Academy that we should set about banning advertising & sports sponsorship, fast food outlets near schools and celebrity endorsement. Let alone introducing "fat taxes".

There really isn't a growing obesity crisis and doctors should help people who get too fat rather than seek to punish the vast majority who never get past being slightly chubby.

....

On alcohol statistics...

****

The chart in this blog from Straight Statistics' Nigel Hawkes underlines the lie of an increasing alcohol problem:

An increasing problem? Seems not.

....

Dying for a drink (or not as the case may be)!

****

While it seems relatively quiet so far, we can expect that "alcohol-related deaths have risen" will become the preferred argument of temperance campaigners, nannying fussbuckets and the Church of Public Health:

Alcohol related deaths in the UK have increased slightly between 2009 and 2010, according to official figures. The number of deaths linked to drinking has gone from 8,664 to 8,790 - a rise of 126. The Office for National Statistics said the increase was due to more deaths in men.

So should we be "doing something" about this scourge? Well, the official figures (and accompanying narrative) are quite helpful. Firstly the ONS point out that whatever the current strategy* looks like, it seems to be working:

GLF data also show that alcohol consumption for both males and females tended to increase until 2000–02 and declined thereafter (data available to 2009, 2010 data on alcohol consumption will be available in March 2011 in the GLF (ONS, 2011b)).

So we are drinking less but more of us are dying from drink. Again the statisticians helpfully explain this:

However, despite an apparent decrease in alcohol consumption, it is likely that it will take a number of years for any resulting reduction in alcohol-related deaths to become apparent as diseases associated with excessive alcohol consumption are often slow to develop. For example, Alcoholic Liver Disease, the most prevalent of all alcohol-related causes of death included in this bulletin, responsible for approximately 64 per cent of all alcohol-related deaths in 2010, takes approximately ten years to develop.

So we should start to see a decline in alcohol-related deaths from around 2012. Obviously, this remains to be seen but in no way can this very slight increase in 2010 (after a fall in 2009) be set as a argument for draconian intervention - minimum pricing and so forth.


*You know that strategy - 24-hour drinking, liberalised licensing, a grown-up attitude to drinking? The one that the prohibitionists and Daily Mail want to stop!
....

On the matter of lunatic statistical projections....

****

...this one is a real winner!

It would take 1.4 million years to clear the backlog of northern families waiting for social housing if the housing market does not improve, the National Housing Federation has said.

What are these people on?

....

Who to believe?

****

Two articles from Inside Housing:

Firstly:

According to figures for the first six months of 2011, housebuilders registered nine per cent more new homes compared to the same period in 2010 - from 58,571 to 63,832.

 Of these, public sector registrations were up from 20,182 in 2010 to 23,132 in 2011 - an increase of 15 per cent.

And then there's:

Construction of public housing has fallen in the second quarter of 2011 as spending cuts begin to hit.

 According to the latest Royal Institute of Chartered Surveyors construction market survey, there was a 17 per cent rise in chartered surveyors reporting a fall in the level of public housing construction.

Hey ho!


....

Alcohol Concern Cymru - the most ignorant of nannying fussbuckets

****

Although BBC Wales does its best to make Alcohol Concern Cymru not seem like a bunch of idiots even they can't quite manage it with this story:

An alcohol charity claims there a "silent epidemic" of heavy drinking among elderly people in Wales

But Alcohol Concern Cymru's (AAC) report quotes statistics that have been challenged by drinks industry body The Portman Group. The group argued overall trends showed "a positive and continuing decline in the rates of excessive drinking".

Andrew Misell of AAC said there was anecdotal evidence from elderly support workers to back their claim.

All your typical row until you get to look at why AAC issued their scary press release:

The paper compares figures from Welsh Government-commissioned Health Surveys of 2003/4 and 2009 as "evidence that the proportion of older people drinking more than the recommended amount is rising".


AAC said the number of over 65s who said they had drunk more than the recommended maximum in the previous week rose from 22% (men) and 7% (women) in 2003/4 to 34% (men) and 17% (women) in 2009.

See scary - a huge increase in wrinkly boozing is evidenced from the surveys. Except that - as the BBC eventually explain:
 

However, BBC Wales understands that as a result of changes in methodology adopted by the compilers of the Welsh Health Survey in 2006 the two sets of statistics are not comparable.

Ah, there you are you see! No increase in drinking. However AAC keep wriggling:

When challenged on the paper's use of statistics Mr Misell said: "Those statistics were taken as an illustration. It's certainly the case that more work needs to be done in terms of finding out what exactly is the pattern of drinking among older people.


"The point of the paper is that it's a hidden problem. If you talk to people working with older people they will say there's quite a lot of anecdotal evidence to support the fact that alcohol is a problem."

The problem is so hidden that the statistics can't pick it up and are showing old folk drinking less rather than more. Something must be done!

....