Definition
The p-value is the probability of obtaining a result at least as extreme as the one observed if the null hypothesis (e.g. "the groups do not differ") were true. A small p-value (usually below 0.05) means the observed difference is poorly compatible with the null hypothesis — which is why you reject it.
Foundations & hypothesis testing
A p-value is neither the probability that a hypothesis is true nor a measure of effect size. It only says how surprising the data are assuming no effect exists. A huge sample yields a "significant" p even for a practically irrelevant difference; a small sample may miss an important one.
Therefore always report the p-value together with an effect size and a confidence interval. The 0.05 threshold is a convention — clinical research or many simultaneous tests call for a stricter one (multiple-testing correction).
In Statistica
Statistica shows p-values in the results tables of every test and highlights significant results in red (the threshold is adjustable). The Statistical Advisor and the guide Which statistical test to choose tell you where to get the p-value for a specific question.
Related terms
- Significance level and Type I / Type II errorsThe significance level α is the maximum risk of a Type I error — rejecting a null hypothesis that is actually true (a false alarm).
- Confidence intervalA confidence interval is a range of values that, with a stated confidence (most often 95 %), covers the true value of a…
- Effect sizeEffect size expresses how large a difference is or how strong an association is — independently of sample size.
- Statistical power and sample sizeStatistical power is the probability that a test detects an effect that really exists (1 − β).
- t-testThe t-test compares means: the one-sample version compares a mean with a fixed value, the two-sample version the means…
Knowledgebase guides
FAQ
- Is p = 0.06 "almost significant"?
- No — it is a non-significant result at the 0.05 level. Report it honestly with the effect size and confidence interval; the threshold is a convention, not a law of nature.
- What does p < 0.001 mean?
- That a result this extreme would occur less than once in a thousand times if the null hypothesis were true. It still says nothing about the size or practical relevance of the difference.
- Why does Statistica highlight results in red?
- The default highlighting marks p below 0.05. You can change the threshold in the module settings — useful with a stricter criterion.
Try it on your own data
Statistica free for 30 days
Full version, no credit card. Or get a pricing estimate in a minute.
Foundations & hypothesis testing
Updated: September 2026.