Polls and Polling – What are the chances that one is right and another is wrong?
Political races spawn a bewildering number of polls; some make you almost giddy, others are devastating. A problem arises when they seem to be measuring the same thing. What’s to believe?
A polling aggregation blog, FiveThirtyEight.com, created by Nate Silver during the 2008 elections became well-known for it success in balancing out comparative polls and weighting their results by looking at their historical track record, sample size, selection method and timeliness. It became a regular NY Times feature this year.
Here is something to think about from a post the other day:
“On Tuesday, polls conducted by the firm Rasmussen Reports — which released more than 100 surveys in the final three weeks of the campaign, including some commissioned under a subsidiary on behalf of Fox News — badly missed the margin in many states, and also exhibited a considerable bias toward Republican candidates.
Other polling firms, like SurveyUSA and Quinnipiac University, produced more reliable results in Senate and gubernatorial races. A firm that conducts surveys by Internet, YouGov, also performed relatively well.”
To read more, go to :
In another post the terms house effects and bias when used in statistics are discussed – bias is a bit different than you might think. Knowing the distinction is useful, but if statistics make your eyes glaze over, a quick glance at the following should be sufficient.