πŸ“Š Statistics & Probability

P Value Calculator

Calculate p-value from a z-score or t-score. Free p-value calculator for one-tailed and two-tailed tests.

Loading calculator…
Share: WhatsApp Facebook X / Twitter

What This Calculator Tells You

This calculator converts a z-score into a p-value: the probability of seeing a result at least that extreme if there were really no effect. It also tells you whether the result clears the common 0.05 significance threshold.

Use it when you already have a z-statistic β€” from an A/B test, a survey comparison or a textbook problem β€” and need the matching p-value.

What to Enter

  • Z-score β€” your test statistic. Positive or negative; the calculator uses its size.
  • Tails (1 or 2) β€” use 2 (the default) when a difference in either direction matters, which is the usual case. Use 1 only if you decided in advance that you only care about one direction.

Worked Examples

1. The famous 1.96

z = 1.96, two-tailed.

  • Result β†’ p = 0.0500 β€” exactly at the conventional threshold. This is why 1.96 is the critical value for 95% confidence.

2. A significant A/B test

An A/B test with 10,000 visitors per variant and conversion rates of 4.0% vs 4.8% produced z = 2.758.

3. One-tailed vs two-tailed

  • z = 1.645, one-tailed β†’ p = 0.0500.
  • z = 1.5, two-tailed β†’ p = 0.1336 β€” not significant. The same z-score gives half that p-value one-tailed (about 0.067), which is why choosing tails after seeing the data is a form of cheating.

How It’s Calculated

For z-test (two-tailed): p = 2 Γ— (1 βˆ’ Ξ¦(|z|)) where Ξ¦ is the standard normal CDF.

How to Read Your Result

  • p < 0.05: conventionally "statistically significant" β€” a result this extreme would happen less than 5% of the time with no real effect.
  • p β‰₯ 0.05: not enough evidence to rule out chance. Not proof that there is no effect.
  • The p-value is not the probability your hypothesis is true. It assumes no effect and asks how surprising the data is.
  • Report the effect size too. A tiny p-value with a trivial difference is rarely worth acting on.

Common Mistakes to Avoid

  • Switching to one-tailed after the fact to push a result under 0.05.
  • Treating 0.049 and 0.051 as opposites. They represent almost identical evidence.
  • Running many tests and reporting the significant one. With 20 comparisons, one will likely hit p < 0.05 by chance alone.
  • Using a z-test for small samples where a t-test is appropriate.
Built and maintained by GenAlpha Tools Editorial. Formula tested against known answers and edge cases · last reviewed October 2026. How we calculate · Report an error

When to Use This Calculator

  • Convert a z-statistic from a report or paper into a p-value.
  • Double-check A/B test results.
  • Work through statistics homework.
  • Find the significance of a survey comparison.

Frequently Asked Questions

What is a p-value in simple terms?

The chance of getting a result at least as extreme as yours if nothing were really going on. Small p-values suggest something real is happening.

Should I use one or two tails?

Two, unless you committed before collecting data to caring about only one direction. Two-tailed is the safer default.

Why 0.05?

It is a convention, not a law. Some fields use 0.01 or stricter; low-risk business decisions sometimes accept 0.10. Choose the threshold before you look at results.

How is this related to the z-score calculator?

The z-score calculator standardizes a single value. This calculator takes a z-statistic from a test and converts it into a p-value. Read z-scores and p-values explained.

Do you store the values I enter?

No. All calculations happen in your browser. Your data never leaves your device.

Related Guides

Related Calculators