Z-score calculator.
Turn a value into a z-score and percentile, a z-score into a percentile and probability, or a percentile back into a z-score and raw value. Every answer comes with a live normal-curve plot showing exactly where you land.
z = (value − mean) / standard deviation. The percentile assumes a normal distribution.
Reads the percentile, the tail probabilities, and the two-tailed p-value straight off the standard normal curve.
Returns the z-score for that percentile, and the raw value if you give a mean and SD. The 95th percentile is z = 1.64.
Bench turns raw data into z-scores, capability, and control charts with a plain-English read, free.
The method.
A z-score expresses a value as a number of standard deviations from the mean, which makes values from different scales comparable. The percentile reads that z off the normal distribution: the shaded area to the left of your z is the share of values below it.
Going the other way, the inverse normal turns a percentile back into a z-score, and a mean and SD turn that into a raw value, the cut-off score for a target percentile.
It all assumes the data is roughly normal. For heavily skewed data, a percentile from the raw data is more honest than one from the z-score.
The maths, in the open.
z = (value − mean) / standard deviation
Worked example. A value of 120 with mean 100 and SD 15 gives z = 20/15 = 1.33, the ~91st percentile. Reverse it: the 91st percentile is z = 1.33, a value of 120 at that same mean and SD.
Common pitfalls.
The percentile assumes a normal distribution. For skewed data the z-score is still defined but the percentile is misleading, so use a percentile from the raw data instead. And remember the two-tailed p-value answers a different question than the percentile: it is the chance of a value at least this far from the mean in either direction.
Z-scores, answered.
What is a z-score?
A z-score is how many standard deviations a value sits from the mean. A z of +2 means two SD above the mean, around the 97.7th percentile.
What is the z-score formula?
z = (value minus the mean) divided by the standard deviation. A value of 120 with a mean of 100 and SD of 15 gives a z-score of 1.33.
How do you convert a z-score to a percentile?
Read the cumulative normal distribution at that z. This tool does it: a z of 0 is the 50th percentile, +1 is about the 84th.
How do you convert a percentile back to a z-score?
Take the inverse normal of the percentile. The 90th percentile is z = 1.28, the 95th is z = 1.64, the 99th is z = 2.33. Switch to the "From a percentile" mode above and add a mean and SD to get the raw cut-off value too.
What is a good or normal z-score?
Most values fall between -3 and +3. A z-score near 0 is average; beyond about +2 or -2 the value is unusual, sitting in the top or bottom ~2.5%.
Is this calculator free?
Yes, free and no signup, running entirely in your browser.