Percentile

A percentile locates a value within a distribution by stating what percentage of the data falls at or below it. If a test score sits at the 80th percentile, roughly 80% of test-takers scored at or below that mark. Percentiles describe relative standing, not absolute performance — an 80th-percentile score says nothing about how many questions were answered correctly, only how the score compares to everyone else's.

Several familiar statistics are just named percentiles. The median is the 50th percentile — half the data lies below it. The quartiles split the data into fourths: the first quartile (Q1) is the 25th percentile and the third quartile (Q3) is the 75th, and together with the minimum, median, and maximum they form the five-number summary behind box-and-whisker plots. To estimate a percentile rank from a data set, count the values at or below the target value, divide by the total count, and multiply by 100.

Percentiles are everywhere in testing and measurement because they normalize across different scales. Standardized exams report percentile ranks alongside scaled scores, growth charts track a child's height percentile, and strength coaches compare an athlete's test results to normative data tables — a vertical jump in the 90th percentile for the athlete's age and sex is elite regardless of the raw number.

Percentiles appear on a wide range of exams. The GRE and SAT test them in data-interpretation questions (and report your own scores as percentiles), while the CSCS exam expects candidates to interpret normative data tables — placing an athlete's test result in a percentile band to guide program design.