1. Standard Z-Score Formula
For an individual score: Z = (x − μ) / σ. For a sample mean of size n: Z = (x̄ − μ) / (σ / √n). Positive Z-scores fall above the mean; negative Z-scores fall below.
THE TOOLBOX / STATISTICS & MATH LAB
Compute exact Z-scores, percentiles, and left/right/two-tailed P-values with a live shaded normal curve—plus Welch's two-sample T-test and 2×2 Chi-Square independence.
STATISTICS FORMULA REFERENCE
For an individual score: Z = (x − μ) / σ. For a sample mean of size n: Z = (x̄ − μ) / (σ / √n). Positive Z-scores fall above the mean; negative Z-scores fall below.
Need the Z-score for the 90th or 97.5th percentile? Switch to Percentile → Z to invert the standard normal cumulative distribution instantly.
Compare two independent group means without assuming equal variances in the T-Test tab (complete with Cohen's d), or test categorical conversion rates in the Chi-Square tab.
Explore Standard Deviation Calculator, A/B Test Significance Calculator, Significant Figures Calculator, or Permutation & Combination.
| Confidence Level | Significance (α, 2-tailed) | Critical Z-Score (±z*) | Left-Tail Percentile |
|---|---|---|---|
| 80% | 0.20 | ±1.2816 | 90.0% |
| 90% | 0.10 | ±1.6449 | 95.0% |
| 95% | 0.05 | ±1.9600 | 97.5% |
| 98% | 0.02 | ±2.3263 | 99.0% |
| 99% | 0.01 | ±2.5758 | 99.5% |
| 99.9% | 0.001 | ±3.2905 | 99.95% |
A Z-score measures how many standard deviations a raw observation (x) lies above or below the population mean (μ): Z = (x − μ) ÷ σ. For a sample mean of size n, divide σ by √n (the standard error): Z = (x̄ − μ) ÷ (σ / √n).
Enter your Z-score in the "From Z-Score" tab. The cumulative left-tail area P(Z < z) gives your percentile rank, P(Z > z) gives the upper-tail p-value, and 2 × P(Z > |z|) gives the two-tailed p-value used in standard hypothesis tests.
For a two-tailed 95% confidence level (α = 0.05), the critical Z-score is ±1.960. For 90% confidence (α = 0.10) it is ±1.645, and for 99% confidence (α = 0.01) it is ±2.576.
Use a Z-test when the population standard deviation (σ) is known or sample size is large. Use Welch’s Two-Sample T-Test when comparing two sample means with unknown population variance.
A p-value below 0.05 means that if the null hypothesis were true, observing a test statistic at least as extreme as yours would occur less than 5% of the time—providing conventional evidence to reject the null hypothesis.