Go to A Distant Drum of the Coming Revolution
- Add a comment
- Go to Bush's approval polls hit all time low
Bush shouldn't automatically get everything he wants!
Shocking from me, isn't it? Input from both parties is needed. Make that positive, constructive, forward-thinking input. Sadly, the Democrats have been rather short of that lately.
posted by
WriterofLight
on April 25, 2005 at 7:57 PM
| link to this | reply
"then why should anyone believe those statements about their participants being a representative cross-section?"
Because it IS possible to build a sample with a cross-section that is representative of the population as a whole. For example, if you are interested in gauging the opinion of all adults in the United States, and you know (via census data or whatever) that, say, 51% of the adult population is female, then you can manipulate your sample (the people whose answers are counted) so that the proportion of women is also 51%. What Harris is saying they can't control, or at least they can't quantify, are things like question order. Actually the disclaimer that they put at the end of their article is the first disclaimer of its kind that I've seen, even though what they say would apply to all similar polls. So I think it's a sign of integrity that they included it.
Anyway, polls aside, it seems clear to me that Bush isn't automatically getting his way on everything, the way he was before. His social security proposals, for one thing, are going over like a wet balloon.
posted by
Eeek
on April 20, 2005 at 10:24 PM
| link to this | reply
This may be terribly disingenuous of me . . .
. . . but, Eeek, if the data concerning this poll - be it from poorly framed questions or poor reporting of results - is as inaccurate as it appears, then why should anyone believe those statements about their participants being a representative cross-section?
And, Jane, Glenn has actually been rather nice since he started reading my stuff again.
posted by
WriterofLight
on April 20, 2005 at 7:22 PM
| link to this | reply
Statistics is a science
Or, at least it can be. There are ways to calculate how accurate it is to use a particular sample size to gauge the opinions of a much larger population -- there are specific formulas used to do this. So the relatively small sample size
by itself does not mean a poll is inaccurate.
At the end of the article (the one giving the Harris poll results) there are answers to some of the questions that you had about the demographics:
The Harris Poll® was conducted by telephone within the United States between April 5 and 10, 2005 among a nationwide cross section of 1,010 adults (aged 18 and over). Figures for age, sex, race, education, region and household income were weighted where necessary to bring them into line with their actual proportions in the population. Propensity score weighting was also used to adjust for respondents’ propensity to be online.
And, reading further, the Harris people themselves admit that this kind of polling isn't an EXACT science:
In theory, with probability samples of this size, one could say with 95 percent certainty that the results have a sampling error of plus or minus 3 percentage points. Unfortunately, there are several other possible sources of error in all polls or surveys that are probably more serious than theoretical calculations of sampling error. They include refusals to be interviewed (nonresponse), question wording and question order, and weighting. It is impossible to quantify the errors that may result from these factors.
So, you're right to an extent. The poll may be off by some unknown factor. Probably the best way to interpret polls is to look at more than one, and to look for trends over time. And I think the trends do show that Bush is a lot less popular now then he was during the election.
posted by
Eeek
on April 20, 2005 at 2:26 PM
| link to this | reply
we give far too much credibility to polls. In general I think they're a
waste of time.
I've been away from blogit for awhile. I see glennb hasn't changed a bit, eh?
posted by
JanesOpinion
on April 19, 2005 at 4:55 PM
| link to this | reply
Writeroflight,
Will the wonders ever cease?
posted by
Glennb
on April 19, 2005 at 6:48 AM
| link to this | reply
This is getting dangerous!
Assuming he's serious about disregarding the polls, that's two points Glenn and I agree on
posted by
WriterofLight
on April 18, 2005 at 7:58 PM
| link to this | reply
Writeroflight,
Who cares what this clown's poll ratings are? Bring him up on charges for his incompetence and malfeasance! Then watch me pay attention!
posted by
Glennb
on April 18, 2005 at 7:36 PM
| link to this | reply