The Bullshit Asymmetry Principle: Torturing Statistics

The Bullshit Asymmetry Principle: Torturing Statistics

It must be something about this time of year for all the idiotic anti-vaping, anti-nicotine or anti-anything, to crawl out from under whatever rock they’ve been hiding under and spout a tranche of utter bullshit before scuttling back to their safe space, complete with a shiny new grant to cook up more bullshit.

Today saw the on-line release of three, well two, actually - one of them was an opinion piece - papers in the Journal of the American Academy of Pediatrics. It seems that AAP are ever so friendly with a certain rotund “professor” at UCSF, as one of these papers is his.

Of course, his paper doesn’t add anything meaningful to the science already out there. All this one does is rehash the figures and stats from the National Youth Tobacco Survey. Up until 2014. It doesn’t even take into account the data collected in the last two years. There’s a reason for that of course; it’d skew his preconception.

The second of the three papers, laughingly entitled “Adolescent Risk Behaviors and Use of Electronic Vapor Products and Cigarettes” concludes that those who smoke or vape or even dual-use are more likely to take risks. Well, no fucking shit Sherlock!

Good grief, are these opponents (or proponents of an over-exaggerated implementation of the Precautionary Principle) really that stuck for ideas on how to try and nix the e-cigarette market? Or is it just a case that the NIH has so much loose cash sloshing around that it needs to spend before its next budget?

Aside from the grandiose claim of:

The introduction of e-cigarettes was not associated with a change in the linear decline in cigarette smoking among youth but is expanding overall use. E-cigarette–only users would be unlikely to have initiated tobacco product use with cigarettes.

In the “what this study adds” co-authored by the rotund rascal, it is quite simply an exercise in torturing data to fit a particular narrative - as one comes to expect from the US.

“Ever smokers” were those who responded “yes” to “Have you ever tried cigarette smoking, even 1 or 2 puffs?” “Current smokers” reported the use of cigarettes during the past 30 days on at least 1 day.

Once again, the definitions give the rotund reaver broad scope to manipulate the data as he sees fit. But it gets worse than that:

Never smokers with a missing response for 30-day smoking were considered noncurrent smokers. Never e-cigarette users with a missing response for 30-day e-cigarette use were considered noncurrent e-cigarette users.

In short, if there was missing data were still considered smokers or vapers. I suppose it didn’t occur to the rotund reaver to think that missing data could suggest that the participant didn’t smoke or vape at all? Of course not, that doesn’t fit the narrative.

If that was the only flaw, I’d stop there. But it isn’t. This is the Rotund Reaver at his finest ladies and gents!

We examined psychosocial risk factors for cigarette smoking or e-cigarette use identified in previous research that were also available for the 2004–2014 NYTS data.

In other words, we took additional data (from outside the NYTS) and mixed them together. Two data sources folks! Confounding abound! But this is the Rotund Reaver, he of course adjusted for those with regression analyses as if that solves everything!

That data was then used to create a model “to estimate the probability that e-cigarette users would have initiated nicotine use with cigarettes” in other words, looking for the gateway effect. Again. It’s become something of an obsession with the Rotund Reaver.

h/t Clive Bates

h/t Clive Bates

All the data from the CDC, the Monitoring the Future survey and the NYTS all show a decline in traditional cigarette smoking. Even at the time of introduction of e-cigarettes to the US in 2009, there had been a marked decline in the prevalence rate - which the Rotund Reaver claims isn’t significant. To be fair, it isn’t that significant as the smoking rate had been on a decline for years prior to 2009, but from 2011 onward the prevalence rate declined even more, yet you wouldn’t believe it from the media articles.

Yet the claim made in the conclusion:

the lack of a demonstrable acceleration in the long-term rate of decline in youth smoking prevalence after the introduction of e-cigarettes does not support the hypothesis that this decline is due to youth substituting e-cigarettes for conventional cigarettes. In contrast, the rapid increase in e-cigarette use by youth resulted in higher levels of 30-day use of cigarettes and e-cigarettes in 2014 than in 2011. The observation that youth who initiate use with e-cigarettes are more likely to start smoking conventional cigarettes.

It is, as always, not supported by the data, as I’ve written about before. This is simply a case of torturing stats to fit a narrative.

The second of the three isn’t that much better. The opening line of the abstract gives away the tone of the paper:

Adolescent use of tobacco in any form is unsafe

Along with the “what this study adds”:

EVP use, alone and concurrent with cigarette smoking, is associated with several health-risk behaviors among high school students. This suggests comprehensive efforts to address health-risk behaviors among adolescents are warranted, including prevention strategies focused on all forms of tobacco use.

So? Kids takes risks. Deal with it. You can’t wrap the little fuckers up in cotton wool for the rest of their lives, or it leads to Generation Snowflake. Oh wait. Never mind, we’re already at that point.

Current cigarette smoking and EVP use were assessed with the following 2 questions: “During the past 30 days, on how many days did you smoke cigarettes?” and “During the past 30 days, on how many days did you use an electronic vapor product?” An introduction to the EVP question was provided to give examples of EVP brands (blu, NJOY, or Starbuzz) and examples of EVP types (e-cigarettes, e-cigars, e-pipes, vape pipes, vaping pens, e-hookahs, and hookah pens).

Good grief! Does anyone in academia in the US actually understand the subject they are investigating? Anyone?

Back in 2015, some intrepid academic types tried to claim there was a link between drinking and smoking/vaping. This is along those very same lines.

Also, I suspect there might be some jealousy involved:

Cigarette-only smokers, EVP-only users, and dual users were more likely than nonusers to engage in several injury, violence, and substance use behaviors; have >4 lifetime sexual partners

But then, what do I know?

Teens will experiment with risky behaviour, it’s all part of growing up which renders the final line of this paper:

Additionally, educational and counseling efforts focusing on the harms associated with adolescent tobacco use, including EVPs, are critical.

Completely meaningless. The entire conclusion section is dedicated to proposing population-level interventions to prevent risky behaviour. Risk is a part of growing up and should never be subject to intervention.

(image credit Stefano Carnevali/