-
Yoani Sánchez Uncaged
April 12, 2013 | 163 comments
-
Take the Helmets Off
February 4, 2013 | 68 comments
-
Let’s Pay Women Not to Abort
January 23, 2013 | 69 comments
-
The Millennial Divide
January 22, 2013 | 30 comments
-
The Meaninglessness of Opinion Polls on Roe v. Wade
January 17, 2013 | 68 comments
Political Hay
Polling’s Station
Opinion polls are pervasive. But can we trust them?
The Tea Party’s emergence and the Democrats’ decline. Public backlashes to Obamacare and the “Ground Zero Mosque.” Murmurings about the president’s religious faith and the field of prospective 2012 GOP presidential hopefuls.
Think of any recent political headline and odds are it can be linked to opinion polling.
In the past, opinion polls weren’t very reliable (remember the headline “Dewey Defeats Truman”? It can be blamed on faulty polling), but at least their objective was modest: to capture public opinion.
Today’s polls just as often drive the news cycle and create public opinion. Given the pervasiveness of polls, the question is: Can we trust them?
I visited a few polling firms’ websites and discovered polls on everything from Americans’ feelings about Daylight Saving Time (a plurality thinks it’s not “worth the hassle”) to which country’s citizens feel safest “walking alone at night” (Singapore’s).
We used to get polls predicting whether the president would be re-elected. Now we also get polls telling us how people feel about his choice of pet or vacation spot.
But as polls have become more prominent, so have charges that they are politically motivated. Rush Limbaugh has accused Gallup of “doing everything they can …to keep Obama’s approval at 50 percent.” And Eric Boehlert of the liberal Media Matters claims pollster Scott Rasmussen’s data “looks like it all comes out of the RNC.”
White House Press Secretary Robert Gibbs once complained about a Gallup poll showing President Obama’s approval rating dipping to 47 percent. “If I was a heart patient and Gallup was my EKG, I’d visit my doctor,” he griped. “I’m sure a six-year-old with a crayon could do something not unlike that. I don’t put a lot of stake in, never have, in the EKG that is the daily Gallup trend. I don’t pay a lot of attention to meaninglessness.”
But the Obama administration has sometimes been very happy to talk up Gallup’s meaninglessness, er, findings. When Gallup polling showed initial public support for stimulus spending in early 2009, President Obama told reporters, “I think if you took a look at the Gallup poll yesterday, the American people don’t need convincing.”
No pollster attracts more criticism than Rasmussen. His daily presidential tracking polls consistently show Obama’s approval rating about five percentage points lower than other pollsters.
Political liberals, according to a Politico story, insist that Rasmussen’s polls are, “at best, the result of a flawed polling model and, at worst, designed to undermine Democratic politicians and the party’s national agenda.”
But Rasmussen’s polls were among the most accurate in predicting outcomes in the 2004 and 2006 elections. The liberal website FiveThirtyEight.com gave him the third-highest mark for accuracy in predicting the outcome of the 2008 primaries. Rasmussen was accurate again this year, with the only major miss its projection that Sharron Angle would defeat Harry Reid in Nevada by four points. (Reid won by five points.)
Politics aside, there are many challenges to achieving accurate poll results. These include survey bias resulting from how questions are worded, and sample bias caused by non-random samples of the population.
Every word used in a poll question can affect respondents’ answers. For instance, a February CBS/New York Times poll found that 70 percent of Americans favor gay men and lesbians serving in the military. But the same poll found that just 59 percent of Americans favor homosexuals serving in the military.
It would seem to be a distinction without a difference. But 11 percent of respondents apparently consider the military service of “gay men and lesbians” more acceptable than that of “homosexuals.” Go figure.
About the Author
Daniel Allott is a writer in Washington, D.C.
Letter to the Editor View all comments (16) | Leave a comment
More Articles by Daniel Allott
More Articles From Political Hay
http://spectator.org/archives/2010/12/01/pollings-station
Follow us:
ADVERTISEMENT
Current Issue
- Consternated Conferences
- A Nation on the Edge
- Inside the Gates of Eden
SPONSORED LINKS
FLASHBACK TO: 1995
-
Pope Culture
A man of faith in a godless age is hitting Americans where it hurts.
-
Why the GOP Does Not, Like, Totally Suck
Mr. and Mrs. American Spectator Reader, let P.J. O’Rourke talk sense to your kids.
-
Dames at Sea
-
In the Absence of Guns
In Britain, defending your property can get you life.
-
The Metaphysical Martini
-
Counting the Costs of Clintonism
The debacle of this president’s administration is both a cause and a symptom of the decline of American values. Unless Congress impeaches him, that decline will go on unchecked. An eminent jurist surveys the damage and assesses the chances for the recovery of our culture.
-
Chuck McHagel
It won’t take long for conservatives to scratch this presidential wannabe off their 2008 scorecard.
-
The Legacy of Old John and Mother Fresh-Roasted
-
It’s the Best Time of the Year
The American Christmas, like the songs that celebrate it, makes room for everybody under the rainbow. Is that why so many people seem to be hostile to it?
-
The Bush Crack-Up
Was the President done in by the economy, or by the politics of the economy?
Clip of the Day
ADVERTISEMENT
Coal Miner's Son| 12.1.10 @ 7:47AM
"There are three kinds of lies: Lies. Damned Lies, and Statistics"---Mark Twain.
David W| 12.1.10 @ 2:45PM
and three kinds of lers - liers, damn liers, and statisticians. I never believe polls. I've developed surveys as part of work and non-work efforts. With little background I know that the wording and sampling size/group can skew the results one way or the other.
Alan Brooks| 12.1.10 @ 8:47PM
Agreed with Mark Twain.
IMO figures lie, and liars figure; yet that includes GOP pollsters-- everyone is grinding an ax, McCain as well.
And I trust the GOP less than the Dems.
Curly Smith| 12.1.10 @ 8:40AM
It's all in how you ask the question. If you read the post in the sidebar "Cantor and ObamaCare Repeal" you'll find that Cantor presumably supports forcing insurers to cover those with pre-existing conditions. According to Rush, it's because it polls well.
A pollster could the question in two different ways:
Do you think insurers should be forced to cover those with pre-existing conditions? (a large percentage would likely say "YES!!")
Forcing insurers to cover those with pre-existing conditions would raise premiums for all other policyholders. Do you think insurers should be forced to cover those with pre-existing conditions? (a large percentage would likely say "NO!!!!!")
Leaders lead and followers follow. If your life revolves around reading polls then you're not a leader. Why don't we just replace Congress with an online voting system? If "leadership" merely involves giving us what we say we want then why do we need the middleman and his graft-laden system?
BG| 12.1.10 @ 10:56AM
There's a greater problem with "sampling." Polling accuracies are directly related to the randomness of the sample.... But in the political arena, there is no truly random event. The Sample is already heavily skewed with Liberals having the far advantage.
Just think about it.... Conservatives are generally working between 8-5, they are by nature reluctant to participate in a poll of any kind, and are at best passive-aggressive with whatever is being asked of them! They don't want to give any pollster the time of day!
Liberals, on the other hand, love to be the center of attention. They fit right in with the kind of person who will respond to the pollsters, being more than willing to engage with everybody about anything, no matter how personal, seeing it as an outlet for their naricissism.
Further, whereas Conservationves will decline to participate rather than lie or missrepresent themselves, Liberals know that masquerading as a Conservative will likely get their opinion processed, while at the same time upsetting what others see Conservatives as thinking.
In other words, "random sampling" is almost an impossibility to assure. Because of the nature of Liberal personalities. they will always be over-sampled. Having taught graduate-level statistics and sampling for may years, I know this to be a fact! It's the nature of the beast... thought pollsters don't want anybody to know this!
Ned| 12.1.10 @ 12:45PM
That sample bias is one of the things that Rasmussen adjusts for - as he describes it, Dims are over-sampled. By making those adjustments, he reduces the impact of liberal group-think, and improves the accuracy of his polls... which leads directly to his vilification by the left... they see only "reduces the impact of liberal group-think" and call it bias, purposefully ignoring that it "improves the accuracy of his polls"...
BG| 12.1.10 @ 2:11PM
That's true, and that's why he and others are vilified by the Left. Still, the means by which Ramussen et al attempt to compensate is still guess-work at best, and a poor attempt in the least because of their time-tables... as you know, even vocabulary is subject to bias as per the political group-think one belongs.... the questions themselves and their presented order are never really adequeatedly tested nor analysed for content or accuracy as noted by the author. Forced-choice agendas are notorious for giving false positives. And guess what, the Liberal mind excells in that exact test-taking agenda, as it points to a sociopathology of those well practiced in deceit and slight of hand.... Go figure!
Ken Roberts | 12.1.10 @ 11:27AM
No they can not be trusted at all, the people wanting to change America have gotten control of that as well. today I see where 90 % of those polled no type or what kind of people just those that were polled said nothing would hurt the military if don't ask don't tell were to be repealed, but I also happened to see a poll taken of the soldiers and a solid 63% were against doing away with don't ask don't tell . so it depends on which poll one believes. polls are somewhat useless any more . Can you imagine if you are sharing a fox hole with someone that is gay the ribbing that would take place from your fellow soldiers . Being a soldier at one time I can . I have never seen a time such as this where the minority rules, it has got to change and soon.
Ray| 12.1.10 @ 1:45PM
There is one pervasive "problem" with "opinion" polls that can never be overcome, and that is human nature itself. Opinions change over time, even in the short term. A given poll may indicate the general population's "opinion" when the poll was taken (never mind how "accurate" the poll may claim be, that's yet another matter of opinion), but that opinion is constantly changing so it's darn near impossible to determine just what the general opinion is just a few days after the polls was taken unless you take another poll. As a historical device, it's very useful. As an analytical device, it's useless.
I look at it this way: an opinion poll is as historical device (a means of recording historical information), and the data should not as a analytical tool, the "data collected" shouldn't be used in statistical analysis, for the results of statistical analysis is only accurate when the subject of study is static, unchanging.
Yes, we can use statistical analysis to determine, predict, how many peanuts are in a jar, but that's because the size and shape of peanuts don't change much once they're put into that jar. Human opinion changes constantly so we can't use statistical analysis to determine, predict, who will win the next election, or even how "popular" someone or something will be a month from now.
Intelligent Design| 12.1.10 @ 1:52PM
Are you in favor of completely eliminating the federal income tax system, along with 67,000 pages of regulations and the IRS, replacing revenue with a simple national sales tax?
Has any major pollster asked that question?
DodAederen| 12.1.10 @ 3:27PM
For I am involved in mankind.
Therefore, send not to know
For whom the cell polls,
It polls for thee.
Richard| 12.1.10 @ 4:16PM
The poll question I most despise is; "Do you think the country is headed in the right direction?"
There are enough variables in that question to make the answers meaningless.
Just try jotting down on a piece of paper the combinations and permutations of a lefty and a righty comparing what each thinks he is seeing to what actually is happening versus what he wants to see. Suggestion - use a new roll of TP on which to record your findings in portrait, not landscape, format.
Tom Daniels| 12.1.10 @ 9:29PM
Article: "Rasmussen was accurate again this year, with the only major miss its projection that Sharron Angle would defeat Harry Reid in Nevada by four points."
I'm sorry that Mr Allott does not understand the difference between bias and accuracy. Mr Allott, like Rasmussen, are both inaccurate and biased in this claim.
Accuracy has to do with how far off polls are on average. Bias has to do with the average direction of error. Accuracy shows how well the poll was conducted. Bias shows how honest the poll was.
In terms of accuracy, Rasmussen was on average 4% off, which was more than every other major poll.
In terms of bias, they consistently showed Republican bias. An elementary probability theory analysis shows that with at least 99.9% confidence, the data from Rasmussen was slanted towards Republicans. A more complex analysis moves that probability well over 99.9999%. These analyses have been well documented on the web: anyone with a little statistical knowledge can verify them.
As for the claim that Nevada was the only major mistake from Rasmussen, have a look at how Rasmussen did on Hawaii (the largest error ever recorded by any poll), Delaware, West Virginia, Alaska, Ohio, California, and Colorado Senate races. All were erroneous outside the error margins of Rasmussen's polls.