DISQUS

Not To Be Trusted With Knives: Blog Posting From the Bus

  • Darren · 1 year ago
    The tech-savvy, at-risk youth are the kids behind Dan Savage's most excellent podcast. And I've always wondered about them. I hope he puts them on the air at some point.

    What can I obtain with my 25 points? A Kewpie doll?
  • Beth · 1 year ago
    Nicely done! You answered that one in record time.

    As for the points, I haven't actually decided what they are for. Sort of like that British comedy improv show (that, like most British shows, was later ripped off by the Americans), "Whose Line is it Anyway?" where "everything is made up and the points don't matter." I may someday figure out what the points are for, so make sure you keep them in a safe place!
  • Raul · 1 year ago
    Holy smokes, Darren was fast!

    On the research geeky side - What kind of data would you use to show causation? In the social sciences, causation is perhaps the toughest proof of them all, particularly because most explanations for specific phenomena are of a multiplicitous nature.
  • Beth · 1 year ago
    Randomized, double-blind, placebo-controlled trial. Of course, technically this doesn't prove causation, as there's always the possibility that what looks like causation actually occurred by chance (which is why you will hear "p<0.05 = significant findings" - this means that there's less than a 5% chance that the findings occurred by chance. But at least with a randomized, double-blind, placebo-controlled trial, you've manipulated one factor (A) and examined the effect on another factor (B). When all you have is that (A) is correlated with (B), how would you know if A causes B or B causes or A? (Or C causes both A and B)?
  • Kalev · 1 year ago
    Wow... proof that Twitter isn't as great as it thinks it is! Yay!
  • Tod · 1 year ago
    What? There was no actual value to the points?! I call shenanigans! (I've never actually called shenanigans before. Is that all I do? Will they come now?)