What is the Z-Score to Probability Calculator?
This tool converts a z-score (the number of standard deviations a value lies from the mean) into a probability using the standard normal cumulative distribution function (CDF), denoted \(\Phi(z)\). Probabilities are the foundation of hypothesis testing, confidence intervals, and percentile rankings, so turning a z into a probability is one of the most common tasks in statistics.
How to use it
Enter your z-score and choose the probability type. Left tail gives \(P(Z < z)\) — the area to the left of z, which is the percentile. Right tail gives \(P(Z > z)\), useful for one-sided significance tests. Two-tailed gives \(P(|Z| > |z|)\), the combined area in both tails, used for two-sided tests. The result also shows all three values so you can pick whichever you need.
The formula explained
The standard normal distribution has mean 0 and standard deviation 1. Its CDF is written using the error function:
$$\Phi(z) = \frac{1}{2}\left[1 + \operatorname{erf}\!\left(\frac{z}{\sqrt{2}}\right)\right]$$
Because erf has no closed form, this calculator uses the Abramowitz & Stegun rational approximation (7.1.26), accurate to about \(1.5\times10^{-7}\) — more than enough for practical statistics.
Worked example
For \(z = 1.96\), the left-tail probability \(\Phi(1.96) \approx 0.975\). That means 97.5% of the distribution lies below 1.96. The right tail is $$1 - 0.975 = 0.025,$$ and the two-tailed value is $$2 \times 0.025 = 0.05$$ — which is exactly the familiar 5% significance threshold.
Interpreting Your Z-Score Probability
Left-tail: percentile rank
The left-tail value \(\Phi(z)\) is the proportion of the distribution at or below your z-score. A z of 1 has \(\Phi(1)\approx 0.8413\), so the value sits at about the 84th percentile. A z of 0 is the median (50th percentile).
Right-tail and two-tailed: p-values
- Right-tail \(1-\Phi(z)\) is the p-value for a one-sided test of whether a value is unusually high.
- Left-tail \(\Phi(z)\) is the p-value for a one-sided test of whether a value is unusually low.
- Two-tailed \(2\,\min\{\Phi(z),1-\Phi(z)\}\) is the p-value for a test that counts extreme values in either direction.
A result is called statistically significant at level α if the p-value is at most α. For a two-tailed test, α = 0.05 corresponds to |z| ≥ 1.96 and α = 0.01 to |z| ≥ 2.576. For a one-sided test, α = 0.05 corresponds to z ≥ 1.645 (or z ≤ -1.645) and α = 0.01 to |z| ≥ 2.326.
Judging unusual values
- |z| > 2: about 4.55% of a normal distribution lies this far out in both tails combined, so these values are often called unusual.
- |z| > 3: about 0.27% lies this far out in both tails combined (roughly 1 in 370), so these values are often called very unusual or outliers.
These cutoffs are conventions, not strict laws.
Caveat: normality
The probabilities are exact only if the data (or the test statistic) follow a normal distribution. For skewed or heavy-tailed data, the real tail probabilities can differ substantially from these values. For a test statistic, the z approximation relies on conditions such as a large enough sample size or a known population standard deviation. When those conditions fail, other distributions (such as Student's t) may be more appropriate.
FAQ
What does a z-score of 0 give? \(\Phi(0) = 0.5\), since exactly half the distribution lies below the mean.
Can z be negative? Yes. A negative z gives a left-tail probability below 0.5; the symmetry \(\Phi(-z) = 1 - \Phi(z)\) holds.
Which probability is the p-value? For a one-sided test use the appropriate tail; for a two-sided test use the two-tailed value.