What this calculator does
A p-value summarizes how compatible a test statistic is with a null hypothesis. This calculator uses a z-statistic and the standard normal distribution, then reports the p-value for one or two tails and whether it meets the conventional 0.05 threshold. The calculation is a translation, not a verdict: it depends on the test being set up correctly, the tail choice being made before looking at the data, and the null model being appropriate.
How to use it
- Enter the z-statistic; negative values are allowed.
- Choose a one-tailed or two-tailed test before interpreting the result.
- Read the p-value and the note about the 0.05 threshold.
- Compare the p-value with the significance level chosen for your study.
How it works
Example calculations
Example 1: z = 1.96, two-tailed
The two-tailed p-value is 0.0500. This sits exactly at the 0.05 cutoff, so it is usually described as borderline rather than strong evidence. The one-tailed p-value for the same z is 0.0250.
Example 2: z = 2.58, two-tailed
The two-tailed p-value is 0.0099. That is below 0.05, so the result is statistically significant at the conventional threshold. The one-tailed p-value is 0.0049.
Example 3: z = -1.5, one-tailed
Using the tail in the direction of the observed effect gives p = 0.0668. That is above 0.05, so it is not significant at that threshold. The two-tailed p-value would be 0.1336.
What the result means
A p-value is not the probability that the null hypothesis is true, nor is it the probability that the result is due to chance. It is the probability of seeing data at least as extreme as yours if the null and test assumptions hold. A threshold of 0.05 is a convention, not a law; a result just under it is weak evidence, and a result just over it is not proof of no effect. Statistical significance also differs from practical importance. Tail choice matters: a one-tailed test can halve the p-value, so choose the tail before seeing results. Report the effect size and confidence interval alongside the p-value.
Common mistakes
- Choosing a one-tailed or two-tailed test after seeing which result looks better.
- Reading the p-value as the probability that the null hypothesis is true.
- Treating p greater than 0.05 as proof that there is no effect.
- Using 0.05 as an automatic decision rule without considering context.
- Applying a z test when the population standard deviation is unknown and the sample is small.
Assumptions and limits
- The test statistic follows a standard normal distribution under the null hypothesis.
- Observations are independent, or the test accounts for the study design.
- The tail choice was specified before the data were examined.
- The z-statistic was calculated correctly from the sample and null value.
- The sample is large enough, or the population standard deviation is known.
Frequently asked questions
What does a p-value of 0.05 mean?
It means results at least as extreme as the observed one would occur about 5% of the time if the null hypothesis and test assumptions were true. It is not a 5% chance that the null is true.
When should I use a one-tailed test?
Use it only when the question predicts a direction in advance. Do not choose the tail after seeing the data.
Can a p-value be negative?
No. A p-value is a probability from 0 to 1. A negative result usually means the input or z-statistic is wrong.
Why is a large effect not significant?
The sample may be small or noisy. A large effect from a small sample can still have a large p-value.
Does a small p-value prove causation?
No. It measures compatibility with a null model, not causation. Study design, confounding, and bias matter.
What z-score is significant at 0.05?
For a two-tailed test, the critical values are about -1.96 and 1.96; for one-tailed, about 1.645 in the chosen direction.
Sources
2026 update
How to use the professional output
This page is not just a formula box. The result is designed to be checked, compared, and taken away.
- Professional worksheet. The result includes the inputs used, the method and scope, and a one-variable sensitivity check for finance calculators.
- A/B scenarios. Save two input sets in the browser and compare the primary, secondary, and breakdown figures side by side.
- Print / PDF and CSV. Print a branded worksheet, or export the year-by-year table when the calculator produces one.
The formulas and assumptions above still govern the number. The worksheet makes the estimate auditable; it does not make it a lender quote, tax return, or personalized advice.
Go deeper
