Built in Lahore, PakistanHow we check the math
Math

Z-Score Calculator

Find how many standard deviations a value is from the mean, and what share of a normal distribution falls below it, for test scores, measurements or quality control.

1.5z-score

Formula(85 − 70) ÷ 10
Share of values below x93.32%
Share above x6.68%
Within ±|z| of the mean86.64%

Percentiles assume the data follows a normal (bell-shaped) distribution.

How this calculator works

A z-score (also called a standard score) counts how many standard deviations a value sits from the mean of its distribution. The formula is z = (x − mean) ÷ standard deviation. A z of +1.5 means 1.5 standard deviations above the mean; a z of −2 means 2 standard deviations below.

The point of standardising to a z-score is to put values from different distributions on the same scale. A SAT math score of 650 (mean 500, SD 100 → z = 1.5) and an ACT math score of 28 (mean 21, SD 5 → z = 1.4) can be compared directly: the SAT score was slightly higher in standardised terms.

For data that is roughly normally distributed (bell-shaped), the z-score converts directly to a percentile using the standard normal cumulative distribution. A z of 1.5 corresponds to roughly the 93rd percentile — 93% of values in a normal distribution fall below it. The calculator looks up the exact cumulative probability for each z.

The 68-95-99.7 rule gives quick sanity checks on normal data: about 68% of values fall within ±1 standard deviation of the mean, 95% within ±1.96 (often rounded to ±2), and 99.7% within ±3. These numbers come from the normal distribution's cumulative density.

The calculator also shows the two-tailed probability |z| or more: for z = 2.0 that is 0.0455, meaning about 4.55% of a normal distribution lies more than 2 standard deviations from its mean. This is used directly in hypothesis testing — a |z| of 1.96 corresponds to the two-tailed 5% significance level.

For data that is clearly not normal (incomes, waiting times, sports scores with a hard upper limit), the z-score is still well-defined and still useful as a relative-position measure, but the percentile conversion from the normal table is wrong. Use the data's empirical distribution or a non-parametric percentile rank instead.

Worked example

A test score of 85 where the class mean is 70 and the standard deviation is 10

  1. z = (85 − 70) ÷ 10 = 15 ÷ 10 = 1.5.
  2. The score is 1.5 standard deviations above the mean.
  3. In a normal distribution the cumulative probability at z = 1.5 is 0.9332, so about 93.32% of scores fall below 85.
  4. The score is roughly the 93rd percentile.
  5. Two-tailed probability (score this extreme in either direction): 2 × (1 − 0.9332) = 0.1336, so about 13.36% of scores are further from the mean than this one.

Common mistakes

  • Reading the percentile from a normal table when the data is clearly skewed. Percentiles only line up with z-scores for roughly normal distributions.
  • Using the standard deviation of a sample without Bessel's correction (dividing by n instead of n − 1) when the data is a sample. The z-score is correct in formula but the SD input is biased low.
  • Treating z as a probability. z = 1.5 is a count of standard deviations; the cumulative probability at z = 1.5 is 0.9332.

Limitations of this calculator

  • Percentile output assumes a normal distribution. For non-normal data the ranking is right but the percentage is not.
  • Requires the population mean and standard deviation. For small samples, the Student's t-distribution is more appropriate.
  • Does not perform hypothesis testing or report confidence intervals; it reports standardised position and cumulative probability only.

For your specific situation, consult a tax professional or financial advisor.

Questions people ask

What does a negative z-score mean?

The value is below the mean. z = −1 is one standard deviation below (about the 16th percentile in a normal distribution); z = −2 is two below (about the 2.3rd percentile). The negative sign carries no judgement — it just means "below the mean" rather than "above".

What z-score is "statistically significant"?

By common convention, |z| above 1.96 is significant at the two-tailed 5% level, because only 5% of a normal distribution lies further out than that. |z| above 2.58 is significant at the 1% level, and |z| above 3.29 at the 0.1% level. These cut-offs are arbitrary and the right choice depends on the field — physics regularly asks for 5-sigma (|z| ≥ 5), which corresponds to about 1 in 3.5 million.

Can I compare scores from different tests or measurements?

Yes — that is the main reason z-scores exist. Converting each raw score to its z puts them on a common scale defined by the mean and standard deviation of each test, so a value's standing in its own distribution is comparable to another value's standing in a different one.

Where do I get the mean and standard deviation?

From the data itself: the mean, median, mode calculator and the standard deviation calculator both work on a pasted list. In an exam context the mean and SD are often published after the result (SAT, GRE, standardised assessments). In quality control they come from a baseline sample or a target spec.

What are z-tables and p-values?

A z-table gives the cumulative probability under the standard normal curve to the left of each z value. A p-value is the probability (from that same table) of seeing a result at least as extreme as the one observed, if the null hypothesis is true. The calculator shows both the one-sided and two-sided p for the entered z.

Sources

Last reviewed October 2, 2026 · Last reviewed by Muhammad Ahmad on October 31, 2026