Tag Archives: survey

Analysis of the new ASH ecig survey

by Carl V Phillips

One of the nice things about having a scholarly blog is being able to write what are basically extended footnotes for papers. Writing anything other than simple lab reports in the health sciences is extremely difficult for real scholars because of the length constraints: pressure to keep papers too short to do serious analysis and the lack of footnotes. These result from a combination of atavism (to fit more papers into 20th century paper journals), a warped sense of how science works (hint: pronouncements from authority), and a fear that if people knew that actual thoughtful analysis was an option the whole enterprise of churning out thought-free claims would collapse. Since I need to reference the ASH results for a forthcoming paper, and because someone asked me about them, here is my assessment. Continue reading

New French representative survey: 1% of the population has quit smoking thanks to e-cigarettes

by Carl V Phillips

Most of the time when you see survey results about e-cigarettes, they are based on a self-selected convenience sample.  That is, a call to participate is sent out to people who might be interested (convenience) and only those who are particularly inspired do so (self-selection).  This describes the first survey of e-cigarette users ever published (by me and my colleagues), the CASAA surveys, and several other surveys that are widely discussed in the e-cigarette community. The problem with these is that while you can learn a lot from them, drilling down into the stories of successful and dedicated switchers, they completely fail to answer some questions.  In particular, they are often incorrectly cited to make statistical claims that cannot be supported by this type of survey (e.g., what portion of e-cigarette users are still smoking also).  You cannot answer this because it might be (indeed, probably is) that the most dedicated vapers, who have given up smoking entirely, are far more likely to answer.  Similarly, you cannot infer much about that from testimonials or social media, which represent a very self-selected tiny fraction of the population.  The only way to get numbers like that is to start with a representative sample of the whole population of vapers (i.e., everyone in the population is equally likely to be chosen to participate). For obvious reasons it is not possible to create a list of all vapers, so to get to them you need a representative sample of the whole population that is big enough (the expensive part) to get a lot of vapers.  This also has the advantage that you can estimate what portion of the population is vaping.  There has been relatively little of this to date.  One new addition is this survey from France. (The linked document is in the original French, which I cannot read.  I am working and quoting from a third-party translation that I believe is high quality. But anyone who reads the original and has a different opinion about any of the translation, please note it in the comments.) The survey is thanks to Observatoire Français des Drogues et des Toxicomanies (OFDT; French Monitoring Centre for Drugs and Drug Addiction). Continue reading