Voting for Whosamacallit!
Why the Race Is a Lot Closer Than People Think A fascinating look at the sudden emergence of false polls and other anomalies. Lots of good links too.
“One factor (among many) that may contribute to discrepancies between different outfits’ polls in their Bush-Kerry margins . . . is polling firms’ different philosophies as to whether it’s advisable to mathematically adjust their samples%u2014after all the interviews have been completed%u2014to make the percentages of D’s and R’s in their survey sample match the partisan composition that is likely to be evident at the polls on Election Day. The latter can be estimated from exit polls from previous elections, party registration figures (in states where citizens declare a party ID when registering to vote), and surveys.
“(Another issue that often comes up in evaluating pre-election surveys, with which many of you may be familiar, is whether results are reported for ‘registered’ or ‘likely’ voters. That is a different issue from what is being discussed [in this essay]. Whether a pollster reports results for registered voters, likely voters, or both, weighting by party ID is a separate, independent decision.)”
Before anybody even considers a poll, they should read this excellent article, The Dirty Secrets of Pollsters. This was a hotly-discussed point in the recent Canadian federal election.
I hate poles and projections.
They make me feel good and they make me feel bad.
I would perfer the actual count after the election.
Lets amend the constition to eliminate the poles and projections five days before and continueing though the election.
They can do a pole after the election to see how it differs from the actual votes.
If your interested in polling for the upcoming election try: http://www.electoral-vote.com
They have a daily update of polls and a solid analysis of what that translates too in the electoral college. (There’s also a rss feed).