If there’s a charity more careless in its use of statistics than Alcohol Concern, I’d like to know of it.

Its latest offence is a report, One on Every Corner, which attempts to prove a link between the prevalence of alcohol-related hospital admissions in under-18s and the density of off-licenses in the area. It’s a fine follow-up to its report in internet sites and underage drinking which I featured here, and the claim that London crime is supercharged by drink, here.

Under the heading Methodological Qualifications, the new report states: “This study did not set out to establish cause and effect.” Yet the previous page asserts that nearly 10 per cent of all alcohol specific hospital admissions in England, excluding London, are directly attributable to off-licence density, “meaning availability rather than any other external factor is the cause of one in ten of such harms”.

Why exclude London? Because no link was found for the London boroughs, so they were simply excluded to make the other results more persuasive. That’s chicanery, in my book. The explanation given for the failure to find a link in London is that young people there consistently consume less alcohol than the average in England – which is rather a contrast to Alcohol Concern’s earlier claim that alcohol-related crime is twice as high in London as elsewhere.

Let’s assume, for the sake of argument, that the claimed correlation between off-licence density and hospital admissions (London excluded) is correct. Does that prove that off-licences cause drinking? Or maybe that areas where drinking is more common in all age groups can support more off-licences?

You might as well argue that as areas with fewer bank branches tend to be poorer, it’s the absence of banks that causes poverty. Or, as David Poley of the Portman Group puts it: “I expect there is a correlation between wearing gold shirts and winning the football World Cup; this doesn’t mean that if England play in gold shirts they are more likely to win the next World Cup”.  

One could add that the number of convictions for selling alcohol to under-age drinkers is falling, as regulations are more tightly enforced. But Alcohol Concern has an answer to that. It claims that young people access alcohol from off-licenses by getting friends, family, and casual acquaintances to buy it for them. So even if off-licenses aren’t breaking the law, their mere presence on the High Street contributes to more risky drinking.

The statistical analysis underpinning this report is attributed to Dr Nikki Coghill of the University of the West of England. I e-mailed her on Tuesday to try to establish if she was happy with the way her results had been presented. If she replies I’ll add her comments to this post.