Posted on 09/05/2004 4:01:55 AM PDT by dvwjr
Analysis of recent Newsweek/PSRAI post-RNC convention polling data, with derived and revised Kerry and Bush post-convention 'bounces' and poll leads. Comments welcome...
Interesting. I think he is up a tad more perhaps, but think the double-digits was a bit much.
It baffles me as to how any reputable polling organization would let Newsweek do this to their polling. It also baffles me as to why the polling industry doesn't sanction Newsweek.
What is Zogby saying?
But there has to be some control number which would point to "over sampling". Is the control number based on previous sampling, polls asking party affiliation?
Bottom line: IF there were a shift in partisan allegiance, how would the pollster allow for it in his "control number"?
Zogby's internet polls are just infuriating. The polling industry really needs to get a handle on these bogus polls.
So, do you think turning this into somekind of conspriacy theory may be jumping the gun a bit?
First, there is only one good reason to purposely over sample a certain group. I stated that reason, in my first post.
You raise a good question. You can base the 'control number' to weight back to through known data (voter registration information, census data, etc.). You could use a truly random survey of the poputlation. That's not easy, due to refusal bias. Or, you could use a combination of the above.
Known data and census information are dated sources, so a shift in partisan allegience, wouldn't be accounted for.
In my humble opinion, a random sample of the population would be the best way to account for such a shift. Surveys done for the government, usually by colleges, really do a good job of getting the refusal bias out of a survey. They use methods that are cost prohibitive to the private sector, but the government doesn't seem to mind :-)
Polling is not a perfect science. This is especially true with political polls, because likely voters can fluctuate significanly, as voting day approaches. Plus, they are self selected. More people tend to say they are likely to vote, than actually do vote.
Any time you have to weight, you reduce the accuracy of the poll. If they is a major change in the information you are using to weight the data back to, that isn't accounted for, you're in trouble.
In political polls, I look for trends, instead of 'so and so is up by X percent'. I'm liking the trend, right now.
You wrote:
Party affiliation is not a static, unchanging demographic attribute like sex, race, or even religion (which can change, but not readily).
jvwjr addressed that here:
One of my assumptions that some might disagree with is that I feel that the political party affiliation sample composition should remain fairly consistent. Some believe that from month-to-month people re-identify with another party depending on how a particular candidate is faring in the polls. If that were so, then there would not have been any "Reagan Democrats" in the 1980s, they would have converted and become "Reagan Republicans". They may have voted for Ronald Reagan, but they still voted for Democrat congressional candidates, so to me they remain Democrats. I believe that party affiliation changes are slow, not detected nor truly documented by monthly fluctuations by polling organizations.
So his treatment of party affiliation is the result of a deliberate assumption rather than an oversight. In fact, if I've understood correctly, he considers this assumption to be a correction to Newsweek's results.
Thanks. I wonder if polls in the months after 9/11 showed any swings in party allegiance...do you know?
I'm sorry that I missed that. Random sampling is the best method, but 'refusal bias' is a difficult problem to over come.
I lost all respect for Zogby, when I say the way he worded the Presidential approval question. There was no middle ground. So, respondents that said the President was doing average or okay, were grouped with the negative responses. Leaving a middle ground in a rating question is Marketing Research 101. I can only be left with the opinion that he did it purposely to reduce President Bush's approval.
There is far too much self selection bias in Internet polls, even when getting respondents by emailing them, to rely on them.
George W. Bush will win reelection by a margin of at least ten per cent.
You're welcome. I haven't done any political polls for years. I've been polling for radio staions. They poll every week :-) I wondered about the same thing, but I don't know.
I'm betting that it did and will have some effect. The way the Republican convention gave 911 a major role leads me to believe that 911 did and will be effecting voter identification with Republicans.
Who are these 4% of Republicans who would vote for Kerry?
It takes decades to shift party affiliations. Don’t be fooled.
Dear Yardstick,
I agree that long-term party affiliation changes slowly over time.
But I think that a small but significant percentage of respondents will temporarily change their party self-identification in the wake of a party's convention.
By election time, it will have likely shifted back, but for a few days, some number of folks who normally self-identify as Democrat or Independent may identify as Republican.
I know that the ultra liberal fellow who works for me came in after the Republican Convention just about ready to vote for W. At that moment, I think he'd have been a little ashamed to self-identify as a Democrat.
But in a week, I'm sure he'll be back to being a yellow dog Democrat ready to drink Kerry Kool-Aid.
I think this is why pollsters' random samples see increases in the affiliation of the party that just held its convention. It isn't a long-term change, but it does affect the sample in the short term.
sitetest
Dear elfman2,
See post #76.
sitetest
You should be paid for an analysis that is this good. That is some *OUTSTANDING* work. You are clearly showing the numbers behind the numbers.
Bottom line: President Bush's lead is a reliable 8% at this point in time.
5 Legislative Days Left Until The AWB Expires
Nice point. They skewed the poll as much as they could safely get away with: 3%. Our 11% lead is really only 8%.
5 Legislative Days Left Until The AWB Expires
yes--this is what i call using the baboon method... explain it as if you are talking with a baboon and need him to understand...
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.