What is a One Proportion Z-Test Calculator?
A one-proportion z-test (also called a 1-prop z test or single proportion z test) checks whether a population proportion equals a claimed value p₀. It compares the sample proportion p̂ = x/n with p₀ using z = (p̂ − p₀) / √[p₀(1 − p₀)/n], then reads the p-value from the standard normal curve. It is valid when np₀ ≥ 10 and n(1 − p₀) ≥ 10.
What the One Proportion Z-Test Calculator does
This one proportion z test calculator takes the number of successes x, the sample size n and the hypothesized proportion p₀, and returns the z statistic, p-value, critical value and decision at your chosen α. It also checks the success–failure condition, gives a 95% Wilson confidence interval and the 95% 1-prop z interval (Wald) for p, draws the standard normal curve with the rejection region shaded, and writes out every step so you can copy the working.
Use it for yes/no outcomes measured once in one sample: the share of voters who back a measure, the defect rate in a batch, the percentage of customers who renew. It works as a 1 prop z test calculator, a z test for proportions calculator and a z and p value calculator in one: you get the z test statistic and the p-value side by side, for two-tailed, left-tailed or right-tailed alternatives.
The test is also known as the 1 proportion z test, the z test for a proportion, the one sample z test for proportions or the one-sample test of proportion. If you need to compare two groups’ proportions, such as an A/B test, use the Two Proportion Z-Test Calculator. If your data are means rather than counts, use the one-sample z-test for a mean.
How to use the One Proportion Z-Test Calculator
- Choose the alternative hypothesis for p: two-tailed (≠), left-tailed (<) or right-tailed (>). Pick it from your research question before you look at the data.
- Enter the number of successes x: the count of “yes” outcomes, such as 58 households that recycle.
- Enter the sample size n, the total number of observations. x cannot be larger than n.
- Enter the hypothesized proportion p₀ as a decimal (0.4) or a percentage (40%), and set the significance level α, usually 0.05.
- Read z, the p-value and the decision. Check the success–failure note first: if np₀ or n(1 − p₀) is below 10, use the exact binomial test described below instead.
What is a one-proportion z-test and when do you use it?
A one-proportion z-test is a hypothesis test for a single population proportion p. The null hypothesis states that p equals a specific value, H₀: p = p₀, and the alternative says it differs from, is less than or is greater than p₀. The test measures how many standard errors the sample proportion sits from p₀ and turns that distance into a p-value.
Use it when all four of these hold:
- One sample, one yes/no outcome. Each observation is a success or a failure, and you count the successes x out of n.
- A claimed value to test. You have a specific p₀ from a claim, a standard, a past rate or a contract, such as “40% of households recycle” or “no more than 5% defective”.
- Random, independent observations. The sample is random, and if you sample without replacement it is under about 10% of the population.
- Enough expected successes and failures. np₀ ≥ 10 and n(1 − p₀) ≥ 10, so the normal approximation to the binomial is accurate. The calculator checks this for you.
One-proportion z-test formula (1-prop z test formula)
| Symbol | Meaning |
|---|---|
| x | number of successes in the sample |
| n | sample size |
| p̂ | sample proportion, x / n |
| p₀ | population proportion claimed in H₀ |
| z(α/2) | two-tailed critical value, 1.96 for 95% confidence |
The test statistic is the z-score of the sample proportion: the gap p̂ − p₀ divided by the standard deviation of p̂ when H₀ is true. The standard error uses p₀, not p̂, because the test assumes the claim is true.
This calculator uses no continuity correction, matching most introductory textbooks and the TI-84 1-PropZTest. R’s prop.test applies a continuity correction by default, so its p-value is slightly larger; prop.test(x, n, p0, correct = FALSE) reproduces the result here.
One-proportion z-test example (two-tailed)
Do 40% of households recycle?
Problem. A city claims that 40% of households recycle. In a random sample of n = 120 households, x = 58 recycle. Is the true proportion different from 0.40 at α = 0.05? These are the calculator’s default values, so you can check each step above.
- 01Hypotheses: H₀: p = 0.40 against H₁: p ≠ 0.40 (two-tailed).
- 02Conditions: np₀ = 120 × 0.4 = 48 and n(1 − p₀) = 120 × 0.6 = 72, both at least 10.
- 03Sample proportion: p̂ = 58 / 120 = 0.4833.
- 04Standard error: SE = √(0.4 × 0.6 / 120) = √0.002 = 0.0447.
- 05Test statistic: z = (0.4833 − 0.4) / 0.0447 = 1.8634.
- 06p-value: 2 · P(Z ≥ 1.8634) ≈ 0.0624. Critical values are ±1.96, and 1.8634 < 1.96.
Answer. p ≈ 0.062 > 0.05, so fail to reject H₀: the sample does not contradict the 40% claim at the 5% level. Failing to reject is not proof that p = 0.40; the 95% Wilson interval (0.396, 0.572) still allows proportions from about 40% to 57%. A right-tailed test (H₁: p > 0.40), chosen before seeing the data, would give p ≈ 0.0312.
How to calculate a one-proportion z-test by hand
The calculator follows the same six steps you would use on paper. Only a standard normal table, such as the z-table, is needed at the end.
- State the hypotheses. H₀: p = p₀ and H₁: p ≠, < or > p₀. Choose the direction from the question, not from the data.
- Check the conditions. Multiply n by p₀ and by 1 − p₀; both products should be at least 10.
- Find the sample proportion p̂ = x / n.
- Find the standard error under H₀, √[p₀(1 − p₀) / n]. Use p₀ here, not p̂.
- Compute the z statistic, z = (p̂ − p₀) / SE. This is the z-score of the sample proportion.
- Find the p-value and decide. Take the tail area beyond z (double it for a two-tailed test) with a p-value from z calculator, and reject H₀ if p ≤ α, or equivalently if z is beyond the critical value.
Critical values for the one-proportion z-test
Instead of the p-value you can compare z with a critical value. A two-tailed test splits α between both tails, so you reject when |z| > z(α/2); a one-tailed test puts all of α in one tail. The Z Critical Value Calculator gives the cut-off for any α.
| α | Two-tailed, ±z(α/2) | Right-tailed, z(α) | Left-tailed, −z(α) |
|---|---|---|---|
| 0.10 | ±1.6449 | 1.2816 | −1.2816 |
| 0.05 | ±1.9600 | 1.6449 | −1.6449 |
| 0.01 | ±2.5758 | 2.3263 | −2.3263 |
| 0.001 | ±3.2905 | 3.0902 | −3.0902 |
Example 2: is the defect rate above 5%? (right-tailed)
A supplier promises that no more than 5% of parts are defective. An inspector checks a random sample of n = 400 parts and finds x = 29 defective. Test H₀: p = 0.05 against H₁: p > 0.05 at α = 0.05.
- Conditions: np₀ = 400 × 0.05 = 20 and n(1 − p₀) = 380, both at least 10. (Load this example with the “Defect rate above 5%?” button above the calculator.)
- p̂ = 29 / 400 = 0.0725.
- SE = √(0.05 × 0.95 / 400) = √0.00011875 = 0.010897.
- z = (0.0725 − 0.05) / 0.010897 = 2.0647.
- Right-tailed p-value = P(Z ≥ 2.0647) ≈ 0.0195; critical value 1.6449.
- Decision: 2.0647 > 1.6449 and p < 0.05, so reject H₀. The data show the defect rate is above the promised 5%.
1-proportion z interval: when to use it
A 1-proportion z interval (1-PropZInt on a TI-84) estimates p instead of testing a claimed value: p̂ ± z(α/2) · √[p̂(1 − p̂) / n]. Use it when the question is “what is the proportion?” rather than “is it 40%?”. It needs at least 10 observed successes and 10 observed failures, because it uses p̂ in the standard error.
For the recycling sample, the 95% 1-prop z interval is 0.4833 ± 1.96 × 0.0456 = (0.3939, 0.5727). It contains 0.40, which agrees with the two-tailed test failing to reject. The calculator shows this Wald interval and the Wilson interval, which has better coverage in small samples or when p̂ is near 0 or 1; the Proportion Confidence Interval Calculator adds the exact Clopper–Pearson interval and any confidence level.
Because the test uses p₀ in its standard error and the interval uses p̂, the two can disagree near the cut-off. In Example 2 the test rejects (p = 0.0195), yet the 95% Wald interval (0.0471, 0.0979) just includes 0.05. The Wilson interval (0.0510, 0.1022), which inverts the same score test, excludes 0.05 and agrees with it.
When the success–failure condition fails: use the exact binomial test
With small n or p₀ near 0 or 1, the normal curve is a poor fit for the binomial count and the z-test p-value can be badly off. Take x = 4 successes in n = 20 with p₀ = 0.1 (the “Small sample” example in the calculator): np₀ = 2, far below 10. The z-test gives z = 1.4907 and a right-tailed p-value of 0.068, but the exact binomial p-value is P(X ≥ 4) = 0.1330, about twice as large.
In that case report the exact result. The Binomial Distribution Calculator gives P(X ≥ x) or P(X ≤ x) directly for n trials and success probability p₀; for a two-tailed exact test, double the smaller tail (capped at 1).
1-PropZTest on a TI-84, in R and in Excel
The calculator gives the same z and p-value as the common tools, so you can use it to check your work:
- TI-83/TI-84: press STAT, go to TESTS, choose 5:1-PropZTest, enter p₀, x and n, pick ≠p₀, <p₀ or >p₀, then Calculate. For the interval, choose A:1-PropZInt.
- R: prop.test(58, 120, p = 0.4, correct = FALSE) gives X-squared = 3.4722, which is z² = 1.8634², with the same two-tailed p-value of 0.0624. binom.test(58, 120, 0.4) gives the exact test.
- Excel or Google Sheets: compute z in a cell, then =2*(1-NORM.S.DIST(ABS(z),TRUE)) for a two-tailed p-value or =1-NORM.S.DIST(z,TRUE) for a right-tailed one.
1-prop z test vs other z tests and proportion tests
A plain “z test” usually means the one-sample z-test for a mean with a known σ. The one-proportion z-test uses the same standard normal distribution but works with counts, and its standard deviation comes from p₀. Pick by the data you have:
| Test | Data | Null hypothesis | Distribution |
|---|---|---|---|
| One-proportion z-test (this page) | Successes x out of n | p = p₀ | Standard normal |
| One-sample z-test | Mean of measurements, known σ | μ = μ₀ | Standard normal |
| Two-proportion z-test | Successes in two independent groups | p₁ = p₂ | Standard normal |
| Exact binomial test (binomial calculator) | Successes x out of n, small samples | p = p₀ | Binomial |
| Chi-square goodness of fit | Counts in two or more categories | Category shares equal claimed shares | Chi-square |
Common use cases
- Testing a claimed percentage, such as a market share, a pass rate or an approval rating.
- Checking whether a defect or error rate exceeds a contractual limit (right-tailed).
- Comparing a survey result with a known population benchmark, such as a census figure.
- Verifying a click-through, response or conversion rate against a historical baseline.
- Checking homework or an AP Statistics answer worked by hand or on a TI-84.
Assumptions and limitations
- Success–failure condition: np₀ and n(1 − p₀) should both be at least 10 (some books accept 5). When it fails, use an exact binomial test with the Binomial Distribution Calculator.
- Random, independent observations: each trial should be independent, and when sampling without replacement the sample should be under about 10% of the population.
- One proportion only. For two groups use the Two Proportion Z-Test Calculator; for more than two outcome categories use the Chi-Square Goodness of Fit Calculator.
- Significance is not size. A small p-value says the gap from p₀ is unlikely to be chance, not that it matters. Report p̂ and a confidence interval; to estimate p rather than test a value, use the Proportion Confidence Interval Calculator.
- The z-test is an approximation. Reference: NIST/SEMATECH e-Handbook, section 7.2.4: Does the proportion of defectives meet requirements?
Frequently asked questions
What is a one-proportion z-test?
How do you calculate a one-proportion z-test?
How do you calculate the z-score for a proportion?
When do you use a 1-proportion z interval instead of a z-test?
Why does the one-proportion z-test use p₀ in the standard error?
What should I do if np₀ is less than 10?
Is there a one-proportion t-test?
Is a one-proportion z-test the same as a chi-square goodness-of-fit test?
Cite this page
Statculator. (2026, November 14). One Proportion Z-Test Calculator. Retrieved November 14, 2026, from https://statculator.com/hypothesis-tests/one-proportion-z-test-calculator/