Importance of the Margin of Error

The NADbank Study, like most media research studies, is based on a random sample of the market’s population. There are two important statistics that measure the range of error associated with survey results based on a random sample: margin of error and confidence levels.

Margin of Error

The margin of error indicates the level of precision, reported as a + and – figure, associated with the survey result.

Confidence Level

The Margin or Error is usually accompanied with a confidence level. The confidence level is a measure of the number of times out of 100 that the results can be expected to be within the margin of error, 95% being the standard.

The sample and the margin of error are used to calculate the range of values that are deemed correct. For example, in 2008, 71% of adults 18+ in London stated that they read a newspaper in the past week. Based on the incidence and sample size of the London CMA, the margin of error was +/- 3.1 percentage points. At a confidence level of 95%, the results would fall between 67.9% and 74.1%. This range should be incorporated when interpreting survey results. In the 2008 NADbank Study, sample sizes varied from 229, in Sudbury, to 3901, in Toronto.

Tips on using the Margin of Error

  • Survey data provides a range, not a precise value
  • Use the margin of error to test whether year-over-year changes are significant
  • The larger the sample, the less the likelihood of survey “bounce”
  • Look at trends

 

Related Articles