A quick note on polls
Feb. 29th, 2012 10:47 pm![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
maxomaiThe polls I tend to rely upon the most are Rasmussen (lean R), PPP (lean D), and SurveyUSA.
All three tend to be very accurate, certainly according to Nate Silver's research. All three of these polls, also, use computerized phone calls (IVR).
I'm thinking this is not a coincidence; but I can't think of why IVR would be better than traditional live-interview polling. Maybe the live interview poll allows the live interviewer to present a bias? Maybe the live interview polls aren't consistently conducted (as per Murphy)? Perhaps it is indeed just a coincidence.
It would be interesting to see whether some other poll - say, Zogby - improves by switching to IVR. (In Zogby's case, it certainly cannot hurt.)
All three tend to be very accurate, certainly according to Nate Silver's research. All three of these polls, also, use computerized phone calls (IVR).
I'm thinking this is not a coincidence; but I can't think of why IVR would be better than traditional live-interview polling. Maybe the live interview poll allows the live interviewer to present a bias? Maybe the live interview polls aren't consistently conducted (as per Murphy)? Perhaps it is indeed just a coincidence.
It would be interesting to see whether some other poll - say, Zogby - improves by switching to IVR. (In Zogby's case, it certainly cannot hurt.)
