Why didn't you linked to the report instead? This feels like original research, and I doubt that a lot of people will be bothered to verify your claims.
A submission like this should link to the actual study. I don't trust a cable news video to represent the findings accurately and it's hard to have a meaningful or interesting discussion about the methodology without it.
No, I get it, I also find a lot of people who put links in to say "see, this is the definitive proof", I am not one of them; I've only put the paper into the response simply to add a bit more context to the other person's claim (since it was devoid of any form of links or reading material to back up his/her claim). I won't really believe that the study is true until there are more studies done on top of it and been peer reviewed (heck, peer reviewers can even be political!).
Are you reading the actual study? Because what's linked here isn't a study, it's an article about a study. In other words, it's written by a journalist, not a scientist that worked on the study.
Having posted this link, I feel bad for calling attention to a weak study when I'd only read the press release. Yet I'm glad that doing so resulted in someone (Gwern) providing a link to this excellent analytical rebuttal that I probably wouldn't have encountered otherwise.
Well I won't be linking that anymore. Anyways, I was really more interested in the little narrative observation above than the numerical results of the study.
I'm not saying it's an issue with the research. It's very likely the researchers thought of this.
It IS an issue with the article linked here, since it does not explain the research and causes readers to walk away believing there were only 1280 people.
Why? Many of the flaws that jump out at me are not so significant that they would be worthy of concern on their own and I appreciated other people clarifying the group's affiliations(I probably wouldn't have been curious enough to go back and read a bit more otherwise).
Though honestly if this is a scientific study it is very strange that they omitted their methodology entirely(how did they select the data, how did they compare the statistics before and after, how did they account for confounding factors, etc). That is pretty fundamental to this kind of analysis and in its absence I would be hesitant to put much faith in even their weak conclusions.
The graphs themselves are definitely interesting though and I would not at all be surprised if they were on the right track.
reply