Here’s something from Mark Blumenthal that we all kind of expected. Quoting Mark:
Pollsters have fretted for nearly a decade about the growing number of Americans in so-called “cell-phone-only” households that are out of reach of traditional landline telephone poll samples. In previous elections, simple weighting techniques largely corrected for the small statistical bias resulting produced by the missing voters, but the missing slice is now estimated at more than quarter of U.S. households, big enough to affect polling accuracy.
That link in the quote above is from an interesting CDC study. I wonder how Pollsters will deal with this now? I wonder if this had anything to do with Rassmussen’s numbers being off?
Anyway, those are my hit and run observations for this rainy Monday.
- Pew: Skipping Cell Phones Skews Polls to GOP (blogs.wsj.com)
- Republican Bias Found in Polls That Exclude Cellphones (thecaucus.blogs.nytimes.com)
- Want a Republican? Use a Landline. A Democrat? Call a Cell Phone (politicsdaily.com)
- GOP Bias In Landline-Only Polls, Confirms Pew Research (huffingtonpost.com)
- GOP Bias In Landline-Only Polls, Confirms Pew Research (capitolhillblue.com)
- Pew: Growing Cell Phone Poll Bias Favors Republicans (huffingtonpost.com)
- Cell Phones and Election Polls (outsidethebeltway.com)