It really has-been an educational week for many people interesting in polling.
Initially arrived the illuminating disclosure that liberal polling organization Public Policy Polling often doesn’t launch the outcome of polls with unexpected outcomes.
After that arrived this interesting article by TNR’s Nate Cohn, showing that PPP’s polling methodology includes a number of dubious practices these types of as “random deletion” of participants.
Then emerged Nate Silver’s statement which he will stay counting on PPP data even though he thinks PPP’s polls are crap.
Drew Linzer, a Ph.D. political scientist who knows their material, likened arbitrary removal to “intuitive ‘shrinkage’ weighting.”
http://twitter.com/#!/DrewLinzer/status/378192018503000064We’re no specialists, nonetheless it seems like he’s saying this can be a technique always get the sample to mirror the population most importantly.
If it feels like smoke and mirrors, don’t worry, because all pollsters take action:
http://twitter.com/#!/DrewLinzer/status/378190380258193408Really, that’s certainly reassuring.
Relevant: