Free Republic
Browse · Search
News/Activism
Topics · Post Article

To: litany_of_lies
Newsweek's sample is FATALLY FLAWED, because statistically 18% (30% reality minus 12% reported) of the total sample of 1144 who said they were registered really aren't (or a little over 200 people).

Wow!

You just made me feel a whole lot better about this poll.

How quickly did they conduct this poll? There is a lot of pressure on interviewers to get completes. This is especially true, when the poll has to be done quickly.

A scenario where the interviewer puts the respondent in the poll, whether they say they were registered on not, is not hard to believe. I've seen it.

A percentage of the calls are supposed to be monitored by the shift supervisor, but time pressures lead to problems with the results. That's a fact of life in the research business.

32 posted on 10/03/2004 9:54:28 AM PDT by Strider
[ Post Reply | Private Reply | To 31 | View Replies ]


To: Strider

Having done some telemarketing in the past to get people to try to come to focus groups, I can tell you there is a great deal of pressure to find respondents. In our case, we bent the rules or led the person we called on a little bit to get them to say they were a user of a certain product or whatever.

I would think there would be a lot of pressure to take a person at their word when they say they are registered. I think there is also an "embarrassment factor," where people don't want to admit they aren't registered, plus an "importance factor," where people who know they won't be eligible to give their opinion lie about their registration status so they can. (and feel important).


34 posted on 10/03/2004 10:07:27 AM PDT by litany_of_lies
[ Post Reply | Private Reply | To 32 | View Replies ]

Free Republic
Browse · Search
News/Activism
Topics · Post Article


FreeRepublic, LLC, PO BOX 9771, FRESNO, CA 93794
FreeRepublic.com is powered by software copyright 2000-2008 John Robinson