Sunday data/statistics link roundup (12/14/14)

  1. 1. suggests that economists are impartial when it comes to their liberal/conservative views. That being said, I’m not sure the regression line says what they think it does, particularly if you pay attention to the variance around the line (via Rafa).
    1. I am digging the simplicity of charted.co from the folks at Medium. But I worry about spurious correlations everywhere. I guess I should just let that ship sail.
    2. FiveThirtyEight does a run down of the beer mile. If they set up a data crunchers beer mile, we are in.
    3. I love it when Thomas Lumley interviews himself about silly research studies and particularly their associated press releases. I can actually hear his voice in my head when I read them. This time the lipstick/IQ silliness gets Lumleyed.
    4. Jordan was better than Kobe. Surprise. Plus Rafa always takes the Kobe bait.
    5. Matlab/Python/R translation cheat sheet (via Stephanie H.).
    6. If I’ve said it once, I’ve said it a million times, statistical thinking is now as important as reading and writing. The latest example is parents not understanding the difference between sensitivity and the predictive value of a positive may be leading to unnecessary abortions (via Dan M./Rafa).
 
comments powered by Disqus