Opinion poll

Opinion polls are surveys of opinion using sampling. They are designed to represent the opinions of a population by asking a small number of people a series of questions and then extrapolating the answers to the larger group.

Potential for inaccuracy

Margin of error

All polls have a margin of error, which is a function of the number of people polled. The margin of error reflects the effects of chance in the sampling process, but does not reflect other sources of error, such as measurement error, errors in data processing, and non-reprentative samples (see below). A poll with a random sample of 500 people has margin of sampling error of 4.5% for the estimated percentage of the whole population. A 4.5% margin of error means that 95% of the time the procedure used would give an estimate within 4.5% of the percentage to be estimated.

Since people asked to participate in a poll have the right to refuse, poll samples are not representative samples from a population, and their mathematical characteristics may be markedly different from the population's. Since the margin of error differs with the percentage estimated, and since the percentage estimated may be markedly different from that in the population, the margin of error based on the poll results may be inappropriate.

Wording of questions

It is well established that the wording of the questions, and the order in which they are asked, can influence results of polls. Thus comparisons between polls often boil down to the wording of the question. One way in which pollsters attempt to minimize this effect is to ask the same set of questions over time, in order to track changes in opinion. The most effective controls, used by attitude researchers, are:

• asking enough questions to allow all aspects of an issue to be covered and to control effects due to the form of the question (such as positive or negative wording), the adequacy of the number being established quantitatively with psychometric measures such as reliability coefficients, and

• analyzing the results with psychometric techniques which synthesize the answers into a few reliable scores and detect ineffective questions.

These controls are not widely used in the polling industry.

Nonrepresentative samples

Another source of error is the deliberate or accidental use of nonrepresentative samples. For example, telephone sampling has a built-in error because in many times and places, those with telephones have been generally richer than those without. Alternately, in some places, many people have only mobile telephones which pollers can not call for polling purposes, and this can also skew the demographics of the polled population. Polling organizations have developed many weighting techniques to help overcome these deficiencies, to varying degrees of success.

People asked to participate in opinion polls also have the right to refuse; this means that the sample is self-selected and consequently a non-probability sample.

Polling organizations

There are many polling organizations. The most famous is the Gallup poll, created by George Gallup.

Other major polling organizations in the United States include:

Nielsen Ratings, virtually always for television.

All the major television networks, alone or in conjunction with the largest newspapers or magazines, in virtually every country with elections, operate polling operations, alone or in groups.

The best-known failure of opinion polling to date in the United States was the prediction that Thomas Dewey would defeat Harry S. Truman in the 1948 Presidential election. Major polling organizations, including Gallup and the Roper Center, indicated a landslide victory for Dewey.

See also

• Exit poll
• confidence interval
• push poll
• All-Russia Center for the Study of Public Opinion