Bryan Caplan  

Less Liberty Than Meets the Eye

Data on Political Beliefs... More than Corn--it's Wood Chip...

The Gallup poll that Arnold talks about seems to have a shocking result: even though American political discourse obsesses over liberal versus conservative, for every three people who fit these labels, there are two who do not. If you ask one question about whether government should "promote traditional values," and another question about whether "government is trying to do too many things that should be left to individuals and businesses," 24% gives the liberal answers (no; no), 27% gives the conservative answers (yes; yes), 21% gives the libertarian answers (no, yes), and 19% gives the populist answers (yes, no).

This is particularly puzzling because left-right ideology is a very strong predictor of both public opinion and voting. How are these results possible? The answer is that classifications based on TWO yes/no questions are bound to have a lot of measurement error.

To see this, suppose that, in reality, 50% of Americans are liberal and 50% are conservative. Libertarians and populists don't exist at all. Now suppose further that on any given question, people have a 25% chance of giving the wrong answer. Maybe they speak before they think, misunderstand the question, or just want to get off the phone as fast as possible without being rude. What would a pollster find under these assumptions?

Survey says...

56.25% (75% squared) of conservatives would test conservative
6.25% (25% squared) of conservatives would test liberal
18.75% (25%*75%) of conservatives would test libertarian
18.75 (75%*25%) of conservatives would test populist

Just flip the words "conservative" and "liberal" to get analogous results for liberals.

The overall finding, then, would be that Americans are: 31.5% conservative, 31.5% liberal, 18.75% libertarian, and 18.75% populist, even though, by assumption, the last two categories are empty.

It would be great if 21% of Americans were libertarian. But once you consider the power of measurement error to distort results, it is very likely that the Gallup results are overstated. I predict that if you tried to correct for measurement error by (a) sampling the same people repeatedly, (b) asking more questions, or (c) letting respondents give a range of answers ("strongly agree," "slightly agree," etc.) instead of demanding a yes or no, the percentage of libertarian and populist respondents would fall to about half of what Gallup finds. Some of them would turn out to be liberals or conservatives who misspoke; others would turn out to be moderates in disguise.

I wish I were wrong, but come on! If 40% of Americans didn't fit on the liberal-conservative spectrum, we wouldn't need Gallup to point it out.

P.S. Measurement error is probably smaller for more educated respondents. So the finding that Arnold highlights - education predicts libertarianism - is more reliable than the overall results.

Comments and Sharing

TRACKBACKS (3 to date)
TrackBack URL:
The author at The Club for Growth Blog in a related article titled Thursday's Daily News writes:
    Shadegg is Best Hope for GOP Leadership - AZ Republic Editorial The Groundhog Party? - Pittsburgh Tribune-Review Editorial Republican Referendum - Wall Street Journal Editorial For Lou Dobbs, It’s Always Groundhog Day - Pat Cleary, M... [Tracked on February 2, 2006 9:41 AM]
COMMENTS (11 to date)
Paul N writes:

Whose "traditional values"? What "things" should be left to individuals and businesses? Each person who hears these questions will project their own ideas of what specific things they refer to. These questions are too vague for anything to be made of the results.

Lord writes:

Yes. Liberals would leave civil rights to individuals while conservatives would leave social programs to individuals. Liberals would leave religion to individuals while conservatives would leave equality to individuals.

Robert Schwartz writes:

A better hypothesis is that pollsters speak a different language than ordinary Americans. Most people do not have a coherent ideology and will answer specific questions, particularly ones that are not in the front of the public agenda in a very offhand way. Also an enormous amount depends on polling technique, question ordering, pollster-citizen interaction, sample construction, etc. As I always say, you tell me the results you want from a poll and we can get them.

William Anderson writes:

I wonder if there is a basic misunderstanding here.

In some political science work since the early 1990s, the liberal/conservative binary division has been replaced by a four-fold table derived from two axes. Interviewees are asked questions that relate to government intervention in the economy. They are also asked questions related to government intervention in society. If they are pro-government intervention on both, they are "populists." If they are anti on both, they are "libertarians." If they are pro on economic but not social, they are "liberal." Etc.

It seems to me that is the kind of poll we are looking at here. So measurement error is NOT the explanation.

spencer writes:

Why is it that when you find a poll that supports your biases it is great, but if it doesn't polls are no good?

Is that what the taxpapers of the Commonwealth of Virginia pay you to teach your students?

A little more consistency would be appreciated.

Timothy writes:

GMU is a public university? Could've fooled me.

liberty writes:

>It seems to me that is the kind of poll we are looking at here. So measurement error is NOT the explanation.

Why does that mean that error can't explain it?

Daniel writes:

spencer apparently didn't even read the post, otherwise he would have seen that Bryan is knocking a poll that *does* support his beliefs - the poll says that 20% of Americans are libertarian, and he is saying that it is *LESS* than that even though the poll result would be favorable to his side. Come on!

spencer, I've seen you around, over at Cafe Hayek too. It seems that you only come to libertarian blogs to troll ignorantly. How's that workin' out for you?

Bill writes:

Measurement error, fine. But 25%? That seems rather high.

liberty writes:

>Measurement error, fine. But 25%? That seems rather high.

It normally would be, but a poll that asks just a few questions and is sort of vague and depending on how/when/to whom it is asked (eg the example of a quick phone call at dinner time, and of people who may not have thought deeply about the subject before), could potentially have a very high error rate.

Mr. Econotarian writes:

Regardless of polls, the political results are the results of public choice.

Religious bigots (I'm sure they mean well) have joined forces with those who support mildly reasonable economic policies (despite some recent strife between the two).

Religious non-bigots have joined forces with the atheist intellectual socialists.

The two groups carve up the power pie...

Comments for this entry have been closed
Return to top