Calculator
Example Data Table
| Test | Inputs | Expected Focus |
|---|---|---|
| One sample mean | Mean 103, null 100, deviation 12, n 64 | Checks whether the sample mean differs from 100. |
| One sample proportion | 58 successes, n 100, null proportion 0.50 | Checks whether the observed rate differs from 50%. |
| Two means | 82 vs 77, deviations 10 and 9, sizes 50 and 55 | Checks whether two population means differ. |
| Two proportions | 65/120 vs 50/110 | Checks whether two population proportions differ. |
Formula Used
General z statistic: z = (estimate - null value) / standard error.
One mean: SE = σ / √n.
One proportion: SE = √[p0(1 - p0) / n].
Two means: SE = √[(σ1² / n1) + (σ2² / n2)].
Two proportions: SE = √[p1(1 - p1) / n1 + p2(1 - p2) / n2].
Confidence interval: estimate ± z critical × standard error.
P value: the calculator reads the normal curve according to the selected tail.
How to Use This Calculator
- Select the z test type that matches your study.
- Choose a two tailed, greater than, or less than alternative.
- Enter alpha and the desired confidence level.
- Fill only the input group related to your chosen test.
- Press Calculate to view the result above the form.
- Use CSV or PDF export for records and reports.
Z Test Statistic Guide
What the Statistic Means
A z test statistic measures distance from a null value. It uses standard error units. A value near zero means the estimate is close to the claim. A large positive or negative value means the estimate is far from the claim. This calculator supports common z workflows. You can test one mean, one proportion, two means, or two proportions.
When a Z Test Works
A z test works best when the sampling distribution is nearly normal. For means, the population standard deviation should be known or strongly justified. Larger samples also help. For proportions, expected successes and failures should usually be large enough. The tool checks basic inputs, yet sound study design still matters.
Choosing the Tail
The tail setting matches the research question. Use a two tailed test when any difference matters. Use a right tailed test when the estimate should be greater than the null value. Use a left tailed test when it should be lower. The same z score can lead to different p values.
Reading the Result
The p value shows how unusual the result is under the null claim. A small p value gives evidence against the null claim. The decision line compares p with alpha. It should not replace judgment. Look at the estimate, standard error, confidence interval, and context together.
Why Confidence Intervals Help
A confidence interval gives a practical range for the unknown value. It also shows precision. Narrow intervals suggest more stable estimates. Wider intervals often mean small samples or high variation. For two sample tests, the interval describes the difference between groups.
Practical Use
Use this page for homework, reports, audits, and quality checks. Enter realistic values. Select the correct test type. Review warnings before using the conclusion. Then export the results for records. The calculator gives transparent steps, so your work is easier to check.
Keep assumptions in view. A small alpha reduces false alarms, but it can miss real effects. A larger sample can detect smaller differences. Report the test type, tail, alpha, z value, p value, and interval. These details make the result reproducible. They also help readers see whether the finding is statistically clear. Save source data with results.
FAQs
What is a z test statistic?
It is the number of standard errors between your estimate and the null value. A larger absolute z value usually means stronger evidence against the null hypothesis.
When should I use a z test?
Use it when the sampling distribution is approximately normal and the required population standard deviation or proportion assumptions are suitable for your test.
What does the p value mean?
The p value shows how likely a result this extreme is if the null hypothesis is true. Smaller values give stronger evidence against the null.
What is alpha?
Alpha is the chosen significance level. Common values are 0.05, 0.01, and 0.10. The calculator compares the p value with alpha.
What is a two tailed test?
A two tailed test checks for a difference in either direction. It is useful when both higher and lower outcomes matter.
Can I test two proportions?
Yes. Enter successes and sample sizes for both groups. Use pooled standard error when the null difference is zero and assumptions are suitable.
Why do I need population standard deviation for means?
A classic z test for means uses known population standard deviation. If it is unknown and estimated from small samples, a t test may be better.
Can I export the result?
Yes. Use the CSV button before submission or the PDF button after a result appears. Both options help save your calculation summary.