 |
|  |
 |
|  |
 |
|  |
 |
|
Edan
|
|
Zogby: has it at Bush 46 - Kerry 45 (two way), Bush 46 - Kerry 43 (multiparty).
quote: Pollster John Zogby: "The close race got even closer. There is some evidence that Kerry’s debate performance and increased clarity on the war has helped him consolidate at least some of the support that he has lost. But undecideds are up to 8 percent and there is still a month to go. There is also no doubt that Ralph Nader is hurting Kerry. The post convention bounce for Bush is over and his biggest hurdle is among undecided voters who give him a 31 percent positive job performance rating and a 69 percent negative rating. Only 13 percent of undecided voters feel that the president deserves re-election (his lowest yet) while 37 percent feel it is time for someone new.
Undecideds at 8 percent are high because we don’t push them until later. Five points of these are hard undecideds, two-points use to be with Kerry, and one point with Bush. How will they break in the end? Will they even vote? |
All these polls tend to point to one thing - a close race within the margin of errors.
|
|
|  |
 |
|  |
 |
|
Edan
|
|
quote: Originally posted by GePap
We are also not counting on the massive voter registration drives that have occured-there are millions of new voters this election year. Lets see which way they go. |
Also, what percentage of them actually turn out and vote.
|
|
|  |
 |
|
Jon Miller
|
|
its how we do it in science
JM
|
|
|  |
 |
|
Edan
|
|
quote: Originally posted by Jon Miller
its how we do it in science
|
Perhaps, but it seems rather silly to me, considering the sampling differences, different methadologies, different phrasing of the questions, pushing leaners vs. not, two-way races vs multiparty, the occasional outlier poll, taken at different dates, with different margins of error, etc, to tell me, what? That the race is close?
I already know that. 
|
|
|  |
 |
|
Edan
|
|
quote: Originally posted by dv8ed
Um. How does that work? If you have one poll of 600 people and one of 3000, and you just average the percentages, doesn't that add too much weight to the 600 poll? |
If you're just averaging them, yep. Especially as (assuming no bias) the 3000 one likely going to be more accurate than the 600 one.
Now, if you have the internal of the two polls, and the methadologies were the same, you could try to compute a figure weighting the two appropriately, although that wouldn't really lower the margin of error very much. (going from a 3000 size poll to a 3600 size poll only reduces the margin of error by about 00.15%)
|
|
|  |
 |
|
Drachasor
|
|
quote: Originally posted by Jon Miller
its how we do it in science
JM |
You left out the "pseudo-"
-Drachasor
|
|
|  |
All times are GMT. The time now is 05:22. Apolyton Time is 00:22. |
top of page
|
| archivepost |
|
Forum Rules:
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts
|
HTML code is ON
vB code is ON
Smilies are ON
[IMG] code is ON
|
|
|
|
|
|