What is a percentile?
In statistics, a percentile refers to the number where a certain percentage of scores fall below that number. If a result falls in the 20th percentile, for example, it means that this result is higher than 20 percent of all results being compared against it, and below 80 percent of them.
We could also look at it from a non-research perspective. Imagine you have scored 67 out of 90 on a test. That figure has no real meaning unless you know what percentile you fall into, and therefore what is considered to be a “good” score. For instance, if you knew that your score is in the 90th percentile, that means you scored better than 90% of people who took the test and have performed well compared to others.
What is the difference between a mean, a norm, and a percentile?
Both percentiles and norms compare test results against a database:
- A mean is the average score for a measure across respondents in one survey or project. For example, if five people are asked, "On a scale from 1 to 5, how likely are you to recommend this concept to a friend?," and three answer "2" and two answer "4," the mean score for this measure is 2.8.
- A norm represents the average of all tests for a measure in the database. The Zappi platform informs you if your score is statistically higher, lower, or similar to this average.
- A percentile provides more granular information regarding the performance of your test, which is obtained by comparing it with other tests in the database.