I don't think Paul Krugman actually understands probability and statistics. Like, at all: http://krugman.blogs.nytimes.com/2012/11/04/math-is-hard/?smid=tw-NytimesKrugman&seid=auto …
@nothings For 1 tie + 11 Obama polls, only 5 have to be wrong. to produce his "overwhelming" result. This _will_ happen every n elections.
-
-
@cmuratori I'm not sure what you think happens with multiple polls. "An average of many polls will have a much smaller standard error." -
@nothings Only if you assume that they are all correct. But if they were, then you'd only need one of them anyway. And they may overlap. - Show replies
New conversation -
-
-
@cmuratori If you flip a coin 20 times and get "biased" result, could be chance. Repeat exp 10 times, get same bias 9 times: very unlikely.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@cmuratori Basically, I think Krugman's post is a tl;dr for this post: http://fivethirtyeight.blogs.nytimes.com/2012/11/03/nov-2-for-romney-to-win-state-polls-must-be-statistically-biased/ …Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@cmuratori 13 heads to 7 tails isn't noteworthy; 130 to 70 is incredibly suspicious.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.