Binomial Test (one-proportion exact)
VerifiedCategorical
Run this test straight away on a free built-in teaching dataset — no data of your own needed — or bring your own. Either opens the guided workspace: variable setup, assumption diagnostics, results with effect sizes and confidence intervals, figures, and APA-ready reporting.
Loading teaching datasets…
Or use your own dataset
Loading your datasets…
Tests whether a single observed proportion (k successes out of n Bernoulli trials) differs from a pre-specified null proportion p₀.
Uses the EXACT binomial distribution P(X | n, p₀) rather than the normal approximation, so it is valid at any sample size. Reports the exact two-sided p, observed proportion k/n with Clopper-Pearson 95% CI, and the difference from p₀. The small-sample-safe one-proportion test; companion to the asymptotic z-test which is faster but unreliable at small n or extreme p̂.
Worked example
Is a success rate different from chance?
The exact binomial test compares an observed number of successes against a hypothesised probability.
22 successes in 30 trials differed from a .50 rate, exact p = .016.
An exact binomial test showed the success rate (22/30) exceeded .50, p = .016.
When to use it
- One-sample binary outcome with fixed nA diagnostic kit is claimed to have 90% accuracy; the researcher tests it on 100 known cases and counts how many are correctly classified, then compares to p₀ = 0.90.
- Fairness test (coin or single binary outcome with p₀ = 0.5)60 wine-tasters compare two wines and 38 prefer A.
When NOT to — use instead
- Two independent groupsBinomial test is one-sample. → Two-Proportions Z-Test
- Multi-category outcome with hypothesised distributionBinomial is for 2 categories. → Chi-Square Goodness-of-Fit
- No meaningful p₀ benchmarkBinomial test requires a substantively-meaningful null proportion. → Binomial Test (one-proportion exact)
- Paired / repeated binary measurementsBinomial assumes single sample. → McNemar's Test (paired 2\u00d72)
Hypotheses
Parameter tested: population proportion of successes p
Assumptions (and what to do if they fail)
Check: Verify n ≥ 10 for a useful CI width; smaller samples produce very wide intervals.
If violated: With very small n, the CI is extremely wide and most effect sizes cannot be detected.
Check: Cite the source of p₀ in the pre-registration or methods section.
If violated: A poorly chosen p₀ makes the test uninformative even if it reaches significance.
Check: Verify that 'success' has a single operational definition.
If violated: Inconsistent classification biases the observed proportion and invalidates the test.
Ready to run a Binomial Test (one-proportion exact) on your own data?
Guided setup, automatic assumption checks, effect sizes, figures and an APA write-up.
Run this test →