Thursday, March 27, 2008

Pollster Bias

it's nice when polls support your candidate but how do they really work? are they really scientific?

i looked at obama's poll numbers from various pollsters for pennsylvania and they vary greatly. don't you wonder what their source is for the people to call? i've never been called. and when do pollsters make their calls? that matters. how honest are people in their responses? how are the questions asked?

and this rasmussen poll had a simple yet big flaw. it said 56% of the people were less likely to vote for obama after hearing pastor wright's sermons. but what question was asked and whom did they ask: obama or clinton supporters? that matters.

i've also read stories where pollster terry madonna of franklin & marshall college is criticizing obama. if a pollster is biased, say madonna is a mccain or a clinton supporter, can he tip the polls to favor his bias? he can call in areas where he knows his numbers will mesh. he can design questions to elicit the answer he wants.

seems to me that nbc is biased toward obama. no complaints here, but they manage to get more context into their polling.

these polls come out now in reaction to every bitty thing. but it seems polling is really a tool to influence as opposed to measure. once a poll is out, the media can use the polls that justify its positions. pollsters seem to be having a field day.

here are 20 questions that should be asked of pollsters:
Who did the poll?
Who paid for the poll and why was it done?
How many people were interviewed for the survey?
How were those people chosen?
What area (nation, state, or region) or what group (teachers,lawyers, Democratic voters, etc.) were these people chosen from?
Are the results based on the answers of all the people interviewed?
Who should have been interviewed and was not? Or do response rates matter?
When was the poll done?
How were the interviews conducted?
What about polls on the Internet or World Wide Web?
What is the sampling error for the poll results?
Who’s on first?
What other kinds of factors can skew poll results?
What questions were asked?
In what order were the questions asked?
What about "push polls?"
What other polls have been done on this topic? Do they say the same thing? If they are different, why are they different?
What about exit polls?
What else needs to be included in the report of the poll?
So I've asked all the questions. The answers sound good. Should we report the results?