Why Do Pollsters Use Samples?
One of the most important decisions that every pollster has to make is how to allocate the money available for a survey. There are two critical components to a survey: the number of people to interview and the number of questions to ask. On the one hand, for any given budget, the longer the interview (the more questions asked), the fewer the number of respondents (the people who can be interviewed). On the other hand, the larger the sample size, the less information that can be obtained from each one.
This is a critical decision for pollsters to make because a large sample size provides more precise estimates of how many people prefer one candidate over the other or support or oppose a particular policy, for example, gun control. But being able to ask more questions can provide important explanatory information about why some respondents prefer Al Gore over George W. Bush or which kinds of people are likely to favor a ban on assault weapons.
Sampling is one of the most important tools that pollsters have at their disposal. A well-drawn, scientific sample allows a pollster to conduct interviews with only a small fraction of a population but to draw inferences from their responses back to the attitudes or behavior of the entire population. But this can be done reliably and with confidence only if the sample is drawn according to certain laws of probability. When these procedures are followed, pollsters can accurately estimate the opinions of the almost 200