Research 101

By Glenn Iwata and Stephanie Apostol

Research Essentials
A Refresher in Sampling, Margin of Error, and Confidence

Sample Size
We are often asked, how a relatively small number of people can speak for everyone. Market researchers often explain "sampling" to non-researchers by likening it to a big pot of soup- to taste-test the soup, you do not have to eat the whole pot or even a whole bowl's worth. You only have to try a bite. The same is true for public opinion. You don't have to ask every single person in your target population what they think; you only have to ask a few to get the flavor of their opinion.

Margin of Error
A surveys margin of error or sampling error is simply a measure of how "precise" the data are. It is a necessary tool because organizations do not have the time, money or even the need to survey the entire population. Rather, as discussed above, "samples" of the population are taken using various surveying techniques. As a result, it is necessary to know how precisely the results of the sample reflect true feelings of the entire population. As a rule, the lower the margin of error the more accurately the views of those surveyed matches those of the entire population. The margin of error is expressed as plus or minus 5 percent or +5%.

Confidence Intervals
Remember every margin of error has a "confidence interval" or "level" as it is often referred to. It is usually set at 95%. This percentage reflects how frequently any survey result will fall within the margin of error. A 95% confidence level means 95 out of 100 times the result will be within the margin of error.

Putting it All Together
A sample size of 400 has a margin of error of plus or minus 5 percent (+5%) at a 95% level of confidence. This means that 19 out of 20 times (or 95 out of 100), results of the sample will not be off by more than five percentage points of results that would be obtained by interviewing all qualified respondents.

Using the RARF Tax Extension Study as an example, we can demonstrate how this works practically. Interviewing 400 Maricopa County voters would mean that the finding "75% of voters support the extension of the RARF Tax" means in actuality that 70% to 80% of voters support the tax in 95 out of 100 cases. A reduced sample size of 200 would yield a margin of error of +7% and mean the actual percentage falls between 68% and 82% again at the 95% confidence interval.

Margin of Error Made Easy…
Email us at Answers@westgroupresearch.com or call WestGroup at 602-707-0050 to request an Excel work sheet that allows you to easily calculate the margin of error at varying sample sizes. We also have a nifty calculation sheet that determines whether or not a finding is statistically significant-if you ask nicely, we'll send you that one, too!