ex0729: Sampling Bias in Exit Polls
Description
These data are the number of percentage points by which exit polls over
estimated the actual vote for candidate John Kerry in the 2004 U.S.
presidential election, grouped according to the distance of the exit poll
interviewer from the door of the polling location. How strong is the evidence
that the mean Kerry overestimate increases with increasing distance of
interviewer from the door (thus lending evidence to the theory that supporters
of the other candidate, George W Bush, were more inclined to avoid exit
pollsters)?source
Ramsey, F.L. and Schafer, D.W. (2013). The Statistical Sleuth: A
Course in Methods of Data Analysis (3rd ed), Cengage Learning.References
Evaluation of Edison/Mitofsky Election System 2004 prepared by Edison Media
Research and Mitofsky International for the National Election Pool (NEP),
January 15, 2005.
http://abcnews.go.com/images/Politics/EvaluationofEdisonMitofskyElectionSystem.pdf