Pollsters tend to cover their collective a**ses. They give their paymasters (GOP or DEM) the numbers they want till just near the election then close those unrealistic gaps so they are close and don’t look like complete idiots when they are wrong. Well I’ve thought this for a long time but over at The Gormongons they spell it out pretty clearly. Of course we’ll all see soon.
…The Czar stopped looking at day-to-day polling on Friday, when it became clear that all of it had become complete nonsense. Normally at election time, the media polls favor the Democrats in big numbers in order to starve money from the Republican candidates. This works because undecided voters will be reluctant to give political donations to a candidate they think might lose. You want a pay off on your investment right? Well, the polls all say the Democrat is going to win, so….
…Of course, this seems very scientific but it is of course absolute horseshit. It assumes that the fact Democrats average 36-38% of the vote makes a safe baseline for you to beef up the other numbers. You still have no idea whether or not your sample was good. For example, in 1980, the pollsters must have called nearly every Democrat household in the US and very few Republican ones…
Read the details on how it’s done.
Pollsters have a real problem these days… anyone with callerID just does the click-click deal and cuts them off. So what do they get; a 9 percent response rate. So to get 1000 responses they need over 11000 phone calls. Do polls mean anything now? Plus about 20 percent of people don’t even have a home phone.
Dasher on November 5, 2012 at 9:09 AM
I know I don’t answer any political calls from any party.