This one proportion z test calculator checks a sample against a claimed population value p₀. It shows whether your data differs significantly from a claimed value. Enter the number of successes and the sample size, or a sample percent. Then set p₀, the alpha level and the direction of the test. The result gives the z statistic, the p-value, the critical value and the decision, with a normal curve showing the p-value area. An exact binomial test mode covers small samples. A sample proportion is a part-to-whole ratio, the same idea behind our proportion calculator.
What Is a One-Proportion Z-Test?
A one-proportion z-test is a hypothesis test for one categorical variable with two outcomes, such as yes/no or pass/fail. It asks whether the share of successes in a sample is consistent with a hypothesized population proportion, using the standard normal distribution as an approximation to the binomial test.
It is also called the one-sample proportion test. Use it to determine whether a single proportion matches a benchmark, such as an election poll, a defect rate or a claimed success rate. The method belongs to hypothesis testing, and its outcomes are categorical outcomes with two levels.
How to Use the One Proportion Z Test Calculator
Input Your Values
- Successes x and sample size n (or a sample percent and n).
- The claimed proportion p₀ as a percent.
- The significance level α: 0.05, 0.01 or 0.10.
- The alternative: two-tailed (≠), right-tailed (>) or left-tailed (<).
Summary vs Raw Data
The calculator takes summary data. If you have raw binary data, count the successes (the 1s or yes answers) and the total, then type those two numbers. The From a percent mode converts a reported percentage into whole successes and shows the rounding.
One Proportion Z Test Calculator Uses
One page covers every single-sample proportion question. As a proportion test calculator, it compares one observed proportion with an expected proportion. As a one proportion z test calculator with steps, it writes out all seven stages. It is also a one proportion z test calculator with p-value, critical value and decision.
Course books call it a 1-prop z-test calculator. Others say single proportion z-test calculator. Some list it as a one-sample z-test for proportions calculator. Others prefer one-sample proportion z-test calculator. It is a one proportion z-test tool. In general terms it is a proportion z-test calculator. Searches also find it as a one-sample proportion test calculator.
It runs as an online one proportion z test calculator. It is also a free one proportion z test calculator with no sign-up. It doubles as a p-value from z calculator and a z-critical value calculator, so you no longer need a z-table. A two proportion test calculator is the next tool when you compare groups.
Inside, the z-score computation and the p-value computation use the standard normal distribution, and the confidence interval computation adds a Wilson interval for context. The input fields accept whole counts, the output display shows the decision in one line, the graphical output shades the tail area, and the reset button restores the example.
One Proportion Z Test Formula
Formula
z = (p̂ − p₀) ÷ √(p₀(1 − p₀) ÷ n) p̂ = x ÷ n is the sample proportion, p₀ the claimed value, and the denominator the standard error under the null hypothesis.
The test uses p₀, not p̂, in the standard error because the calculation assumes the null hypothesis is true. Under that assumption, z follows a standard normal distribution with μ = 0 and σ = 1.
Step-by-Step Solution
Step 1: State the Hypotheses
H₀: p = p₀. Hₐ: p ≠ p₀, p > p₀ or p < p₀, chosen before looking at the data.
Step 2: State the Significance Level
Pick α, usually 0.05. It is the risk of rejecting a true null hypothesis that you accept.
Step 3: Check the Normal-Approximation Condition
Check that np₀ ≥ 10 and n(1 − p₀) ≥ 10. If either fails, use the exact binomial test instead.
Step 4: Calculate the Test Statistic
Compute p̂, the standard error √(p₀(1 − p₀)/n), and z = (p̂ − p₀)/SE.
Step 5: Find the P-value & Critical Value
The p-value is the tail area beyond z. Critical values at α = 0.05 are ±1.960 (two-tailed) or 1.645 (one-tailed).
Step 6: Make the Decision
Reject the null hypothesis if the p-value is below α, or equivalently if z is beyond the critical value.
Step 7: Write the Conclusion
State the result in context, for example: "At α = 0.05 there is not enough evidence that support differs from 50%."
Choose the Correct One Proportion Test Hypotheses
Is the Population Proportion Different?
Use a two-tailed test when any difference matters, in either direction.
Is the Population Proportion Greater?
Use a right-tailed test when only an increase matters, such as a defect rate rising above a limit.
Is the Population Proportion Less?
Use a left-tailed test when only a decrease matters, such as a pass rate falling short of a claim.
Worked Examples
Election Poll: x = 520 of n = 1,000 vs. p₀ = 0.5
p̂ = 0.52, SE = √(0.25/1000) = 0.01581, z = 1.265. The two-tailed p-value is 0.2059, so at α = 0.05 we fail to reject H₀: the poll does not show a clear majority.
Defect Rate: x = 60 of n = 500 vs. p₀ = 0.10
A manufacturing defect rate limit is 10%. p̂ = 0.12, SE = 0.01342, z = 1.491, and the right-tailed p-value is 0.0680. At α = 0.05 the rise is not significant, though it is worth watching.
Pass Rate: x = 111 of n = 150 vs. p₀ = 0.80
A training provider claims that 80% of its online certification program students pass. In a sample of 150, 111 passed (74%). z = −1.837 and the left-tailed p-value is 0.0331, so at α = 0.05 the data reject the claim.
Comparing two groups, such as 80 of 200 against 60 of 200 conversions in an A/B test, is a different test: use the Two Proportion Z Test Calculator.
Conditions and Assumptions for a 1 Proportion Z Test
- Random sample or randomized experiment.
- Independent observations; the sample is under 10% of the population.
- Binary outcomes: each observation is a success or a failure.
- Success/failure condition: np₀ ≥ 10 and n(1 − p₀) ≥ 10.
How to Interpret the Z Score, P-Value, and Decision
Does a p-value give the probability that the null hypothesis is true?
No. The p-value is the probability of data at least this extreme if H₀ were true, not the probability that H₀ is true.
What does "not enough evidence" mean?
It means the sample is consistent with p₀; it does not prove that p equals p₀. A larger sample might detect a small real difference.
Is the sample proportion the same as the population proportion?
No. p̂ is an estimate from one sample; the population proportion p is the unknown value the test is about.
Does statistical significance mean the effect is important?
No. With a large n, tiny differences become significant. Look at the size of the difference and its interval as well.
Effect Size
Calculate h Effect Size
Cohen's h = 2·asin(√p̂) − 2·asin(√p₀) measures the size of the difference on a scale where 0.2 is small, 0.5 medium and 0.8 large. For the election poll, h = 0.04, a very small effect.
Power Analysis
Power is the chance the test detects a real difference. To plan n before collecting data, use the Sample Size Calculator Proportion, which sizes studies for a target margin or power.
Common Mistakes
- Choosing the tail after seeing the data.
- Using p̂ instead of p₀ in the standard error.
- Running the z-test with fewer than 10 expected successes or failures.
- Reading "fail to reject" as "proved equal".
Alternative Tests
The exact binomial test computes the p-value directly from the binomial distribution and works for any sample size; 3 successes in 20 against p₀ = 30% gives an exact two-sided p of 0.2204. A chi-square goodness-of-fit test with two categories gives the same result as the two-tailed z-test, since χ² = z².
One Proportion Z Test Practice
Each one proportion z test example below has its answer after it.
- x = 58, n = 100, p₀ = 50%, two-tailed. Answer: z = 1.6, p = 0.1096, fail to reject.
- x = 130, n = 200, p₀ = 55%, right-tailed. Answer: z = 2.843, p = 0.0022, reject.
- x = 41, n = 120, p₀ = 40%, left-tailed. Answer: z = −1.304, p = 0.0961, fail to reject.
To calculate z test proportion answers by hand, follow the seven steps. The z test proportion formula above is the whole method. A z test for proportions uses p₀ in the standard error. A z test for one proportion needs only x, n and p₀. A single proportion z test needs one sample. A one sample z test for a share is the same procedure. Each one proportion hypothesis test starts with H₀. The z test sample proportion p̂ is the observed share. The one proportion z score is the distance from p₀ in standard errors.
Students also search for a one proportion z calculator. Others type one proportion test calculator. A few even type test one proportion calculator. A proportion z score calculator gives z. A proportion hypothesis test calculator adds the decision. Use this proportion z test online page, or any one proportion z test online alternative, the same way.
Statistical inference for proportions has a few standard parts. A one sample z test for proportions compares one group with a benchmark. A z test for population proportion uses the null value in the standard error. A statistical significance test for proportions returns a p-value. Hypothesis testing proportions follows the same seven steps every time. A z statistic calculator reports the test statistic. A p-value calculator for proportions converts z into a tail area. A one-tailed proportion test looks in one direction. A two-tailed proportion test looks both ways. The null hypothesis proportion is p₀. The alternative hypothesis proportion states the direction. A confidence interval for proportion data adds context. The standard error of proportion under H₀ is √(p₀(1 − p₀)/n). A pooled proportion appears only in the two-sample version. The sample size for proportion test planning comes from a power target. The power of proportion test results rises with n. Each z score for proportions is read on the standard normal scale. The normal approximation to binomial counts needs np₀ ≥ 10. A proportion difference test compares two groups instead. This online statistics calculator runs every step in your browser.
Before testing, write the alternative hypothesis in words. A z-value beyond the critical z-value means you reject null hypothesis H₀. The hypothesized proportion comes from a claim or a standard. Count the success count in the sample data. Then compare the observed proportion with the claim. Alpha is usually 0.05. The z-critical value is 1.96 for a two-tailed test at α = 0.05, and the normal approximation is accurate when both expected counts reach 10.
One Proportion Z Test FAQ
Why does the test use p₀ in the standard error instead of p̂?
Because the test assumes the null hypothesis is true, so the spread of p̂ is computed at p₀.
When should I use the one-proportion vs. two-proportion test?
Use the one-proportion test to compare one sample with a fixed value, and the two-proportion test to compare two samples.
What sample size do I need?
Enough for np₀ ≥ 10 and n(1 − p₀) ≥ 10, and enough for adequate power. For p₀ = 0.5, at least 20; detecting small effects needs hundreds.
Can I use this for paired data like before/after on the same subjects?
No, paired yes/no data need McNemar's test, because the two measurements are not independent.
How do I choose the tail direction?
Choose it from the research question before seeing the data; use two-tailed when in doubt.
Why is it called a z-test?
Its test statistic is compared with the standard normal (z) distribution.
References
Related Calculators
- Two Proportion Z Test Calculator: compare two proportions with a z test
- Proportion Confidence Interval Calculator: Wilson, Wald and exact intervals for a proportion
- Sample Proportion Calculator: p-hat and its standard error from a sample