Severus wrote:
Might sound stupid, but please don't believe everything you see written in papers or journals. Chances are the one who wrote the paper only read a single study, and most of the time they actually read it without really understanding it.
It's not stupid at all. I don't have anything even close to your credentials, but I did take a fascinating course in college called, "Statistics, Problems and Possibilities." It was a fantastic course because it not only taught us the math behind statistical analysis, it also taught the history and politics behind the development of statistical math. In order to pass the course, we had to understand both the mathematics AND the psychology behind structuring studies properly. The main purpose wasn't to train anyone to go into statistical fields, but to train us to understand actual studies.
The fact is, the vast majority of reports done on studies are done by reporters who don't have a freaking CLUE how to read one. Almost all news reports about studies are based on nothing more than an abstract, and/or the conclusion at the end of the study. Most of these guys have no idea how to tell whether the data is actually interpreted correctly, and in many studies, neither did the people who conducted the study. It's really pretty shameful how bad some of them are.
For our final project, we each chose a study, analyzed it and wrote a report about whether it was a "good" study, or not, and why. I happened to stumble across one of the early vaccine/Autism studies that claimed to prove a connection between the two. It was so full of holes, even I, a one course statistics student could tear it apart easily.
Got an A, by the way. *rubs fingers on chest proudly*
_________________
I'm not likely to be around much longer. As before when I first signed up here years ago, I'm finding that after a long hiatus, and after only a few days back on here, I'm spending way too much time here again already. So I'm requesting my account be locked, banned or whatever. It's just time. Until then, well, I dunno...