Percentile

A percentile is a value below which a given percentage of the observations in a sorted dataset fall — the 25th percentile is the point under which a quarter of the data lies.

Percentiles describe position within a distribution rather than the raw value itself. Saying a measurement is "at the 90th percentile" means 90% of the data is below it and only 10% above — a way to express how high or low something ranks relative to everything else, regardless of the actual units.

How a percentile works in a chart

To find a percentile you sort the data from smallest to largest, then locate the point that splits off that fraction of the values. The 25th percentile (also called the first quartile, or Q1) has a quarter of the data below it; the 50th percentile is the median; the 75th percentile (Q3) has three quarters below. These cut points are exactly what a box plot draws, with the box spanning the 25th to 75th percentiles.

A concrete example

Take the sorted values 2, 4, 6, 8, 10, 12, 14, 16 — eight numbers. The lower quarter is the first two values (2 and 4), so the 25th percentile sits at the boundary just above them, around 5. The median (50th percentile) falls between the 4th and 5th values, 8 and 10, giving 9, since (8 + 10) ÷ 2 = 9. The 75th percentile sits up around 13, with three quarters of the values below it. Together these tell you where the bulk of the data lies.

Related terms

Percentiles at 25, 50 and 75 are the quartiles, and the 50th percentile is the median. They show how data spreads — the same idea visualised in the histogram guide.