A z-score (standard score) tells you how many standard deviations a value lies above or below the mean. A z of 0 is exactly average, +1 is one standard deviation above, −2.5 is two and a half below. Because it strips away the original units, the z-score lets you compare results from different scales (a 82 in a test with mean 70 and SD 8, z = 1.5, against a 640 in a test with mean 500 and SD 100, z = 1.4) or spot values that are unusually far from the rest.
If the data are approximately normally distributed, the z-score also converts into probabilities through the standard normal distribution Φ. The area to the left of z is the percentile: z = 1.5 sits at the 93.3rd percentile. The area to the right is the chance of a value at least that high, and doubling the smaller tail gives the two-tailed p-value used in z-tests. About 68% of normal data lie within ±1, 95% within ±1.96 and 99.7% within ±3.
You can enter the mean and standard deviation directly or paste a data set and let the calculator compute them. To go the other way, from a desired z to the raw value, type the target z into the result and the value field is solved for you, or use the raw score calculator.
How to use the Z-Score Calculator
- Value (x)
- Mean and standard deviation
- Mean (μ)
- Standard deviation (σ)
- Data set
- Standard deviation of the data
- Want to work backwards? Type a value into z-score and Value (x) is calculated for you.
Results update as you type, and everything is calculated in your browser.
How it works
The z-score is (x − μ) ÷ σ. The calculator evaluates the standard normal cumulative distribution Φ at z for the percentile and the tail areas. In data mode, μ is the mean of your values and σ the sample (n − 1) or population (n) standard deviation.
Worked example
A student scores 82 in a test with mean 70 and standard deviation 8. z = (82 − 70) ÷ 8 = 1.5. Φ(1.5) = 0.9332, so about 93.3% of scores fall below 82 and 6.7% above; the two-tailed p-value is 0.134. Using the class data 64, 70, 75, 82, 68, 77, 73, 59 instead, the mean is 71 and the sample SD 7.368, so z = (82 − 71) ÷ 7.368 = 1.49.
Common z-scores and percentiles
| z | Percentile (area below) | Within ±z |
|---|---|---|
| −2 | 2.28% | n/a |
| −1 | 15.87% | n/a |
| 0 | 50% | 0% |
| 1 | 84.13% | 68.27% |
| 1.645 | 95% | 90% |
| 1.96 | 97.5% | 95% |
| 2 | 97.72% | 95.45% |
| 2.576 | 99.5% | 99% |
| 3 | 99.87% | 99.73% |
Inputs explained
| Field | What to enter |
|---|---|
| Value (x) | A number |
| Mean and standard deviation | Choose one: I know μ and σ, Calculate them from a data set |
| Mean (μ) | A number |
| Standard deviation (σ) | A number |
| Data set | A list of numbers separated by commas, spaces or new lines |
| Standard deviation of the data | Choose one: Sample (n − 1), Population (n) |
What each result means
- z-score = ([Value (x)] – [Mean used]) ÷ [SD used]
- Percentile (area below) = ncdf([z-score]) × 100
- Area above = (1 – ncdf([z-score])) × 100
- Two-tailed p-value = 2 × (1 – ncdf(abs([z-score])))
- One-tailed p-value = 1 – ncdf(abs([z-score]))
- Share of values within ±|z| of the mean = (2×ncdf(abs([z-score])) – 1) × 100
- Distance from the mean (x − μ) = [Value (x)] – [Mean used]
- Mean of the data = [Mean used]
- Standard deviation of the data = [SD used]
Formula
z = (x − μ) ÷ σ · percentile = Φ(z) · area above = 1 − Φ(z) · two-tailed p = 2 × (1 − Φ(|z|)) · x = μ + z·σ
Worked example
Inputs: Value (x): 82; Mean and standard deviation: I know μ and σ; Mean (μ): 70; Standard deviation (σ): 8.
Results: z-score = 1.5; Percentile (area below) = 93.32 %; Area above = 6.68 %; Two-tailed p-value = 0.1336; One-tailed p-value = 0.0668; Share of values within ±|z| of the mean = 86.64 %; Distance from the mean (x − μ) = 12; How unusual is it? = Somewhat unusual – 1 to 2 SD from the mean.
Key terms
- Standard deviation
- Typical distance of values from the mean.
- Standard normal distribution
- Normal distribution with mean 0 and SD 1.
- Percentile
- Percentage of values below a given value.
- p-value
- Probability of a result at least as extreme as observed, assuming the null hypothesis.
Frequently asked questions
How do I calculate a z-score?
Subtract the mean from the value and divide by the standard deviation: z = (82 − 70) ÷ 8 = 1.5.
Can a z-score be negative?
Yes. A negative z means the value is below the mean; z = −1 is one standard deviation below.
What percentile is a z-score of 1.5?
Φ(1.5) = 0.9332, the 93.3rd percentile, so 93.3% of a normal population lies below it.
What z-score is the 95th percentile?
About 1.645. The 97.5th percentile is 1.96 and the 99th is 2.326.
Do I need normally distributed data?
Not for the z-score itself. The percentiles and p-values, however, assume the data are approximately normal.
What counts as an outlier?
A common rule flags |z| above 3 (about 0.3% of normal data); some use 2.5. With small samples, prefer the IQR rule from a box plot.
How do I convert a z-score back to a raw score?
x = μ + z·σ. Type the z you want into the result box and the value is solved for you.
Sample or population standard deviation?
Use the population SD when the data are the whole group you are comparing against; use the sample SD when they are a sample from a larger population.
Can I work backwards from the result?
Yes. Type the result you want into z-score and the calculator finds the matching value (x).
Sources
Guides on this topic
- Standard Deviation Explained: How to Calculate It and What It Means: Standard deviation is the typical distance from the mean. Learn to calculate it by hand, when to divide by n − 1, and how to read it with the 68–95–99.7 rule.