General Discussion
Related: Editorials & Other Articles, Issue Forums, Alliance Forums, Region ForumsRasmussen, SurveyUSA and PPP polls exclude cell phones (because they are robopolls) and are biased
for that reason.
when there are multiple polls, one should always look at them in the aggregate and not assume one poll and/or one pollster is the only one that reflects the electorate.
keep these things in mind as you see polls.
remember, polls are just a sample of a universe of the electorate. the chance that they reflect reality is a statistical probability, not an assurance. furthermore, the statistical probability relies on whether the poll actually *randomly* sampled the universe of the electorate and if there is bias introduced, the statistical reliability is suspect.
always read the fine print and the crosstabs --and if they won't share those with you, then think about that!
grains of salt to go with your food for thought.
polichick
(37,152 posts)...and I wonder if most of them aren't doing the same thing.
Edit: typo
WI_DEM
(33,497 posts)Here is an example:
Cell-phone and home-phone respondents included in this research. SurveyUSA interviewed 700 state of Florida adults 10/25/12 through 10/27/12. Of the adults, 643 were registered to vote. Of the registered, 595 were determined by SurveyUSA to have already voted, or to be likely to do so on or before Election Day. This research was conducted using blended sample, mixed-mode. Respondents reachable on a home telephone (71% of likely voters) were interviewed on their home telephone in the recorded voice of a professional announcer. Respondents not reachable on a home telephone (29% of likely voters) were shown a questionnaire on their smartphone, tablet or other electronic device.
http://www.surveyusa.com/
CreekDog
(46,192 posts)they do appear to somehow include them, but they aren't calling them. i wonder how that works (and if it truly does).