Percentile Calculator
Find percentiles from raw data or from Z-scores.
Number
Counts
About this topic
What is a Percentile? The value below which a given percentage of observations fall.
The p-th percentile is the value at which p% of the data lies below it. For example, the 90th percentile is the value below which 90% of the data falls.
Key formulas & rules
- •P50 = median (middle value)
- •P25 = Q1 (first quartile)
- •P75 = Q3 (third quartile)
- •Also called the 'centile'
- •Percentiles range from 0 to 100
- •Uses linear interpolation between points
Examples
| Input | Output | Note |
|---|---|---|
| Data: 1, 2, 3, 4, 5 | P50 = 3 | Median |
| Data: 1..100 | P90 = 90.1 | Near top |
| Data: 1..10 | P25 = 3.25 | First quartile |
| Data: 1..10 | P75 = 7.75 | Third quartile |
Real-world uses
Percentile from Z-Score Convert a standard score to its cumulative probability.
The Z-score tells you how many standard deviations from the mean a value is. The percentile is the cumulative probability up to that Z.
Key formulas & rules
- •Z = (x − μ) / σ
- •Uses the standard normal CDF Φ(z)
- •Z = 0 → 50th percentile (median)
- •Z = 1.645 → 95th percentile
- •Z = 1.96 → 97.5th percentile
- •Z = −1.96 → 2.5th percentile
Examples
| Input | Output | Note |
|---|---|---|
| z = 0 | 50th | Mean |
| z = 1.28 | 90th | Common cutoff |
| z = 2 | 97.7th | Unusually high |
| z = −1 | 15.9th | Below average |
Real-world uses
Quartiles & IQR Divide data into four equal parts.
Quartiles split the ordered data into four groups. The Interquartile Range (IQR) = Q3 − Q1 captures the middle 50% of the data.
Key formulas & rules
- •Q1 = P25, Q2 = P50, Q3 = P75
- •IQR = Q3 − Q1
- •Outlier if x < Q1 − 1.5·IQR
- •Outlier if x > Q3 + 1.5·IQR
- •Robust to extreme values
- •Used in box-and-whisker plots
Examples
| Input | Output | Note |
|---|---|---|
| 1, 2, 3, 4, 5 | Q1=2, Q3=4, IQR=2 | Simple case |
| 1..100 | Q1=25.75, Q3=75.25 | Uniform |
| 1, 2, 100, 101 | Detects outlier | IQR test |
| 1, 2, 3, 4 | Q1=1.75, Q3=3.25 | Interpolation |
Real-world uses
Common Distributions Percentile interpretation across distribution types.
Percentiles have special meaning in different distributions. In a normal distribution, percentiles are determined by Z-scores. In skewed distributions, percentiles shift.
Key formulas & rules
- •Normal: symmetric, mean = median
- •Right-skewed: mean > median
- •Left-skewed: mean < median
- •Bimodal: two peaks, percentile jumps
- •Uniform: every value equally likely
- •Percentile ≠ percentage of correct answers
Examples
| Input | Output | Note |
|---|---|---|
| Normal dist | P50 = mean | Symmetric |
| Right skewed | P50 < mean | Tail on right |
| Bimodal | P50 in valley | Two peaks |
| Left skewed | P50 > mean | Tail on left |
Real-world uses
Modes & formulas
From Raw Data
This matches Excel's PERCENTILE.INC function. It interpolates between adjacent sorted values for a smooth result rather than snapping to the nearest value.
From Z-Score
Φ(z) is the standard normal cumulative distribution function, approximated by the Abramowitz–Stegun method. For example, z = 1.28 corresponds to about the 90th percentile.