Find the value at any percentile rank in your own data set, using the same interpolation method as NumPy.
Recalculated instantly as you edit the data set or the percentile field.
A percentile tells you the value below which a given share of your data falls. The 75th percentile is the value with 75% of the sorted list sitting below it. This calculator sorts your numbers, computes a rank of (k / 100) times (n minus 1), and interpolates between the two nearest values when that rank lands between two positions.
These are all just the same calculation at different values of k, with common shorthand names:
This same idea of ranking a value against a distribution is what the CDC's pediatric growth charts use, though against a large reference population rather than a short list; see the FAQ below. For spread rather than a single cut point, the variance calculator covers the interquartile range concept in more depth.
They're just specific percentiles with their own names. The first quartile is the 25th percentile, the second quartile is the 50th (the median), and the third quartile is the 75th. Deciles split the data into tenths, so the first decile is the 10th percentile and the ninth decile is the 90th. Enter any of those values into the Percentile field to get the same thing this calculator always computes.
Picking the nearest value would make the result jump in steps as k changes, even for a fine-grained request like the 74th versus 75th percentile. Linear interpolation between the two nearest sorted values gives a smooth, unique answer for every percentile, and it's the same default method NumPy and most statistics packages use.
Conceptually yes, mechanically no. A growth chart percentile compares one child's measurement against a large reference population's age- and sex-specific curve built by the CDC, not against a short list you typed in. This calculator finds a percentile within whatever data set you provide; it doesn't have a built-in population reference to compare against.
You get the minimum and maximum of your data set exactly, with no interpolation needed, since both sit at the very ends of the sorted list.