This content originally appeared on NN/g latest articles and announcements and was authored by Raluca Budiu
Summary: A confidence-interval calculation gives a probabilistic estimate of how well a metric obtained from a study explains the behavior of your whole user population.
Collecting metrics in usability studies has become a common practice. We routinely recommend that, whenever you report such a metric, you also include the corresponding confidence interval. But what is a confidence interval?
Let us take a short detour to understand what a confidence interval is. To do so, let’s start with an example from the news, which reports that in May 2021, according to a poll, 79% of people in Canada either have already had a COVID-19 vaccine or will take one as soon as it is available to them.
As you probably well know, the numbers presented in such articles are not based on interviewing the whole population (i.e., all Canadian adults) and getting an answer from every single qualifying person. Instead, they are based on a sample. In the news story above, the Methodology section reveals that the sample included 2000 Canadian adults and that the margin of error for a comparable probability-based random sample of the same size is +/- 2.1%, 19 times out of 20.
Read Full Article
This content originally appeared on NN/g latest articles and announcements and was authored by Raluca Budiu
Raluca Budiu | Sciencx (2021-06-27T16:00:00+00:00) Confidence Intervals, Margins of Error, and Confidence Levels in UX. Retrieved from https://www.scien.cx/2021/06/27/confidence-intervals-margins-of-error-and-confidence-levels-in-ux/
Please log in to upload a file.
There are no updates yet.
Click the Upload button above to add an update.