Exact Binomial Test
The exact binomial test compares an observed number of successes in n independent trials with the binomial distribution under a hypothesized success probability, without relying on approximations.
정확 이항검정은 n번의 독립 시행에서 관측된 성공 횟수를 가정한 성공확률의 이항분포와 근사 없이 직접 비교하는 검정이다.
Out of 20 trials I saw 7 successes; is that consistent with an expected rate of 60 percent?
20번 중 7번 성공했는데, 기대 성공률 60%와 맞는다고 볼 수 있나요?
The exact binomial test computes the probability of outcomes at least as extreme as the observed count directly from the binomial distribution. It is valid for any sample size, and the Clopper-Pearson interval gives an exact confidence interval for the proportion.
When to use Exact Binomial Test
- A single binary outcome is compared with a known or hypothesized proportion.
- The sample is small or the proportion is near zero or one.
- An exact rather than approximate p value is required.
When to use something else
- The sample is large and an approximation suffices; the one-proportion z test gives similar results.
- Two groups are compared; use the two proportion z test or Fisher's exact test.
Assumptions and requirements
- Trials are independent.
- The success probability is the same for every trial.
- The number of trials is fixed in advance.
What the analysis reports
- Number of successes and trials
- Observed proportion
- Exact p value
- Clopper-Pearson confidence interval
How to report it
An exact binomial test indicated that the observed proportion ([k]/[n] = [prop]) differed significantly from [p0], p = [p], 95% CI [[lower], [upper]].
Related methods
Run Exact Binomial Test on Quorant
- Data you need
- a table (CSV or Excel) with an outcome variable
- Price
- 150 credits for one analysis up to 10,000 rows (complexity level 1); larger or wider data costs more. Optional methodologist review: 900 credits.
- Checking
- Checked by property tests in every deployment
- Before you pay
- A free pre-analysis diagnosis checks your data and gives an exact quote; nothing is deducted until you approve it.