Learn how to use statistics to understand the significance of the latest political polling results and to keep yourself from being duped by misleading information.
Why and How are Polls Conducted
Let’s start by talking briefly about how polls are conducted and why they’re taken in the first place. Polls are used to figure out the opinions and preferences of the entire population without having to ask every single person what they think. In other words, the goal is to poll a subset of the entire population (this subset is called a sample) and come up with an answer that is representative of what the population as a whole believes. The most important factor in creating an accurate poll is to come up with a sample that represents the diversity of the entire population. It must be chosen carefully so as not to overrepresent any one group.
That is exactly what it means when you hear reporters say that something is a “scientific poll.” There is indeed a science to choosing an unbiased sample, and polls that employ this science have a much better chance of yielding accurate results. On the other hand, polls taken at news websites, for example, are decidedly unscientific since the population taking the poll is self-selected and is therefore completely biased. In other words, only people who visit that website (and who probably have certain common beliefs) will take the poll—so it cannot be a fair representation of the entire population. Any such self-selected unscientific poll (which many news websites are all too eager to post and report on in an effort to raise viewer involvement) is essentially meaningless—the results are simply too biased to give valuable information about the entire population.
How are Poll Results Reported?
Now that we know how to check whether or not a poll has the potential to be meaningful—whether or not it’s scientific—let’s move on to figuring out whether or not it actually is. That’s right: the fact that a poll has the potential to be meaningful does not necessarily mean that it will give a conclusive result. Let’s take the simple example of a poll measuring the support for two presidential candidates. The result of such a poll is typically reported by giving the percentage of the population supporting candidate A, the percentage supporting candidate B, possibly the percentage of the population that is undecided, and the all-important margin of error.