Posted on 10/17/2004 5:22:13 PM PDT by Perdogg
See link for graph:
Looking at the "RealClear Politics" plot of the presidential polls, I see two long term trendlines, punctuated by a hell of a lot of what I would refer to as "experimental error":
I don't believe that public opinion has been changing as much as these polls seem to suggest. The variation we see up through July looks like what engineers call "sample aliasing" or "jitter". Note that it falls well within the oft-claimed ±4 points of error. This is typical for data taken in noisy sampling environments; I've seen this kind of thing many times.
August and September are different. I've seen that kind of thing, too.
In my opinion, the polls were being deliberately gimmicked, in hopes of helping Kerry. In early August it looks as if there was an attempt to engineer a "post-convention bounce", but it failed and was abandoned after about two weeks. But I'm not absolutely certain about that.
The data for September, however, is clearly an anomaly. The data is much too consistent. Compare the amount of jitter present before September to the data during that month. There's no period before that of comparable length where the data was so stable.
The September data is also drastically outside of previous trends, with distinct stairsteps both at the beginning and at the end. And the data before the anomaly and after it for both Kerry and Bush matches the long term trendlines.
If I saw something like that in scientific or engineering data, I'd be asking a lot of very tough questions. My first suspicion would be that the test equipment was broken, but in the case of opinion polls there is no such thing. My second suspicion would be fraud.
In September, I think there was a deliberate attempt to depress Kerry's numbers, so as to set up an "October comeback". Of course, the goal was to engineer a bandwagon.
Public opinion isn't usually as ephemeral as these polls suggest that it is. But there can be long-term trends, and I find it interesting that such a thing actually does show through. It's quite striking how close some of the data falls to the long term trendlines which I've drawn in.
The reason the Democrats and the MSM are getting frantic is that they're losing.
--------------------------------------------------------------------------------
I don't think there was active collusion among the pollsters, as such. The August anomaly has a clear starting edge, corresponding to the end of the Democratic Convention. But the anomaly fades out; there was no obvious moment the pollsters recognized as being when it should end.
The September anomaly begins just after the Republican convention, and ends with the first debate. That's why there's a sharp stairstep on both edges. No collusion was needed because everyone knew "the script" for September ("temporary Republican convention bounce") and for October ("Kerry comeback because of the debate").
Update: Chris writes:
Take a look of the sampling on the Newsweek polls starting in the middle of August and running through today. I think you'll find it interesting.
Of course, if you don't have time to dig into it, let me sum up: They oversampled Republicans through most of September, then switched back to slightly oversampling Dems, as they feel there are more Democrats than Republicans nationwide.
I figured the data needed a second look as soon as Bush opened that monster lead. There was just no way, no matter how much I'd like to think so.
Oh, and when did they switch back, you ask? Why, right after the first debate, my dear man! Need a point of inflection, after all, don't we?
I remember reading about that. At least they have to be given credit for showing what they did. I would guess the others did the same thing, but may not have admitted it anywhere that's publicly available.
Is a Bear Catholic, Are the Kennedy's Gun Shy?
yep ..... lie cheating stealing scum bags..... lost their franchise..... sold out to 666
> The reason the Democrats and the MSM are getting
> frantic is that they're losing.
There are any number of reasons for the Pravda Press to lie
about poll results. Here are a few:
1. Keep the DNC base from staying home 02 Nov
2. Because even if Kerry can't possibly win, they want to
prevent supermajorities in congress
3. Force the RNC to spend money where they don't need to
4. Have fake numbers to cover vote fraud
Absolutly. The latest polls show an over sampling of republicans. Late next week it will show an oversampling of 'rats and the MSM will declare a Kerry Surge or Groundswell or Tsunami or whatever.
Pollsters are like political consultants. You pay them to tell you what you want to hear. If you tell them what you don't want to hear they go somewhere else. So to stay in business they give you some contrived stuff that passes as statistics, but leave out the good stuff like the null theorem and what alpha they used. Most polls are worthless. The internal polls done by the candidates are the only ones to trust. They are much more carefully done since the spending of ad money is based on them, and it will likely effect the election.
As far as the oversampling argument goes, don't they weight the polls by disgarding responses from the oversampled party until they reach the actual level of "Republican's" or "Democrats" in the voting population.
Hopefully the tightness of the race inspires every republican to GO OUT AND VOTE. Then when it shows the race wasn`t close at all, Kerry runs away to France embarrassed and scorned.
The winner is number 4. To cover voter fraud. Not that just about ever other reason we can come up with doesn't also apply in one way or another.
another reason I heard someone mention is that a close race is better for ratings. people woulld't watch news programs just to hear "Bush is up" day after day.
Yep.. .no doubt.. the MSM and the Pollsters conspiring with funding from George Soros... The message to Georgie boy is that the White House is not for sale... take your liberal agenda and go back to your own country.
Are you guys saying we aren't really ahead? That next week the polls will say Kerry is ahead? Well, who is ahead, then? Does anybody really know?
exactly
Something to remember is that polls are not taken in a vacuum. Like any kind of scientific measurement, opinion dynamics polls measure stimulus response. When the media begins buzzing about an emerging or forthcoming "Kerry comeback", the respondents will respond accordingly. It is not merely how these polls are taken or measured that biases them, it is the way the media reports the story as well. Polls to me have always been much more about media organizations measuring their own message acceptance by the public.
Is clinton a rapist?
To be honest many people I have talked to are voting for Kerry because of Iraq.I argue with them on a daily basis.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.