Reply #104: You're looking at an old version....

[euler]

...of his paper. The new on was released 12/29/2004. Paragraph 3 now reads:

"The pollsters have taken great pains to argue that their polls
were not designed to verify election results, but rather to provide election coverage support to subscribers"

He changed to paragraph in light of what Mitofsky & Lenski ACTUALLY said. He was called on it, and since he's trying to patch the holes in his paper, he had to make the correction.

*************************************************************

"IS this true, that this is the way it has 'aways been done'"

Yes, it is true. I don't know what to say beyond this. If you know how to use Google, do it. The way exit polls are conducted is not a secret. ON EDIT: Go Here:

http://www.mysterypollster.com/main/2004/11/the_difference_.html

*************************************************************

"Why (whether it's the first time, or "always") is it designed this way...why DIDN'T Mitofsky DESIGN the Exit Poll IN ORDER TO verify the election"

This is an easy one. Mitofsky's customer (mainly MSM) tells him what they want from the exit poll, and Mitofsky designs a exit poll that meets their criteria. Europeans decide what *they* want an exit poll to do for them and *they* design a exit poll to meet *their* criteria. MSM likes exit polls that tell them who voted for which candidate and why. Europeans like exit polls that help them verify the integrity of the election. Two differing designs, for two different priority's.

Mitofsky can't simply add other criteria to the ones desired by the customer because the cost of adding criteria to the exit poll would have to come out of his pocket. MSM certainly isn't going to pay Mitofsky for additions to the exit poll they didn't ask for.

Germany, likes to use their exit poll to monitor and verify the election. So, they design a exit poll that guarantees a truly random sample of respondents. What MSM wants from an exit poll does not require a true random sample of respondents and that's what they got. This means that the types of analysis being done by TIA and others, is meaningless. Sorry, but there was a lot of time and effort that was simply wasted by TIA and those who took the time to read most of his posts.

**************************************************************

"It's my opinion that the alteration of the Exit Poll data on everybody's TV screens-- "adjusting" it to match the BushCon controlled "results" --is THE most serious journalistic crime of our era, bar none."

First MSM did not change any numbers, Mitofsky did and the MSM posted them. However, this still does not even qualify as a smoking gun. There are several steps in the exit poll process, where, after the polls close, exit poll data is re weighted to better reflect the actual votes in the precincts. This is basic stuff, so it's hard to understand why so many people still think this is fraudulent. The procedures are well known, and accessible via Google.

One more thing on this. Freeman acknowledges in the latest version of his paper that "survey results originally collected and presented to subscribers were subsequently 'corrected' to conform to official tallies." He then notes that "the pollsters explain this as a natural procedure." The poster to which he refers is Warren Mitofsky. There is an interesting footnote on the same page (Page 3.) It says: "Warren Mitofsky, the founder of Mitofsky International, is credited with having invented the exit poll." Arnebeck, in case 04-2088 says "Warren Mitofsky is a world recognized expert in exit polling." (OH Case 04-2088 Paragraph 66)

Summarizing, if you cant believe the inventor of the exit poll when he says that re weighting to actual vote is the way an exit poll is done, then who are you going to believe ?

*************************************************************

This leads right in to something that I find is a somewhat troubling phenomenon here on DU. Let me establish 3 facts that I think everyone will agree with.

1. TruthIsAll is not a exit poll expert, or a expert statistician. We know this because he told us this in at least two of his posts, so it's on record.

2. Arnebeck and Freeman both recognize that Mitofsky is the inventor of, and a world renowned expert in exit polling. we know this because they wrote this in their papers, so again, it's on record.

3. Warren Mitofsky conducted the very first US presidential election exit poll in 1967 and in the 38 years since then he has conducted 3000 exit polls. (Arnebeck OH Case 04-2088 Paragraph 67)

Now, when TIA (who self describes himself as no exit poll/statistics expert) is confronted with or even shown statements by Mitofsky that contradict statements made in his 'analysis' here on DU, TIA generally offers some disparaging remark about Mitofsky, sneers and says, in effect, that he knows better than Mitofsky how exit polls work, and that he knows better than Mitofsky how exit polling statistics should be done. If that's not bizarre enough, almost every other DU member flocks to his side and agrees with him. This doesn't make any sense at all, does it ? It's all the more puzzling when you see post after post after post where DUer's are complaining about the fact that MSM is not taking us seriously. Well, now you know why.