What it does
A binomial distribution counts the number of successes in a fixed number of independent trials, each with the same chance of success. It is written B(n, p). This lab draws the chart of probabilities for any n up to 50 and any p, and gives P(X = k), P(X ≤ k) and P(X ≥ k) for the k you choose.
The second half runs a one-tailed hypothesis test. You say what chance of success is claimed (the null hypothesis), enter how many successes you observed, choose the direction and a significance level, and the lab gives the probability of a result at least that extreme, the critical region, and whether you would reject the claim. For tests on means and other data, use hypothesis tests, and for building probabilities step by step see probability tree and random variable builder. When n is large, the normal lab shows how the shape becomes bell-shaped.
How to use it
- Set the number of trials n and the probability p.
- Pick a k to see P(X = k), P(X ≤ k) and P(X ≥ k), with the matching bars highlighted.
- In the test box, enter the number of successes you observed, choose whether you suspect p is higher or lower, and pick a significance level.
- Read the probability, the critical region and the conclusion.
- Answer the questions at the bottom.
What each setting does
- n: the number of trials.
- p: the chance of success on each trial.
- k: the number of successes you are asking about.
- Observed successes: what happened in the test.
- Direction: whether the test is for p higher than claimed, or lower.
- Significance level: how unlikely a result must be before you doubt the claim, usually 5%.
Worked example
A fair coin is flipped 20 times, so X ~ B(20, 0.5). P(X = 10) = 0.1762 and P(X ≤ 7) = 0.1316. Suppose someone claims a coin is fair, but you suspect it favours heads, and you see 15 heads. P(X ≥ 15) = 0.0207, which is below 5%, so you reject the claim of fairness. The critical region at 5% is X ≥ 15: any result of 15 or more would lead you to reject.
FAQs
What are the conditions for a binomial model? There is a fixed number of trials, each is independent, each has only two outcomes and the chance of success is the same every time.
Why do we use P(X ≥ 15) and not P(X = 15)? In a test, we ask how likely a result at least as extreme as the one seen is, under the claim being tested.
Does rejecting the claim prove it is false? No. It only says a result this extreme would be unlikely if the claim were true. There is always a small chance of being wrong, which is what the significance level controls.
What if no value reaches the significance level? Then the critical region is empty: even the most extreme result is not unlikely enough, and the lab says so.
Where the numbers come from
- Binomial probabilities P(X = k) = nCk × p^k × (1 − p)^(n − k): standard A-level statistics, the same values as printed binomial tables. Drawings are fibub's own.
Standard scientific values, such as constants, atomic weights and melting points, are facts found in every textbook; we name where ours were checked. If you are an author or publisher and want a value, a credit or a table changed or removed, tell us and we will act quickly.
Last updated 2026-11-16.