Exit Polls

Home > Statistics Every Writer Should Know > The Stats Board > Discusssion

Exit Polls
Message posted by Samantha on November 11, 1999 at 12:00 AM (ET)

I'm trying to prove that exit polls are
not scientifically valid.

any input, whether pro or con
would be appreciated via email.

READERS RESPOND:
(In chronological order. Most recent at the bottom.)

Re: Exit Polls
Message posted by JG on November 11, 1999 at 12:00 AM (ET)

What do you mean by scientifically valid ? What would be an example of poll that you consider to be scientifically valid ? How do you feel exit polls can be made scientifivally valid or do you feel that this is impossible ?
All polling can be easily manipulated - have you heard of push polls etc.
Exit polls are especially vulnerable to poor procedures and inappropriate analysis even if the people involved are honest and only looking for a valid, reliable, meaningful answer .
I can tell you a hundred different way of manipulating a poll while appearing to be 'scientifically correct' .
The only true test of exit polls is if the results are useful. Do they supply a 'reasonable' explantion for what actully happened in the election, do they help predict the next election, do politicians and other professionals take them seriously and find them useful, etc.

Your $5 contribution helps cover part the $500 annual cost of keeping this site online.