Understanding a Two Sample Z Test
A two sample z test compares two independent sample averages. It checks whether their observed difference is large enough to suggest a real population difference. The method works best when population standard deviations are known. It also needs independent samples and suitable sample sizes.
The calculator focuses on mean differences. It accepts each sample mean, each known deviation, and each sample size. It also accepts a hypothesized difference. This value is often zero. A zero value tests whether both population means are equal.
The tool supports two tailed, left tailed, and right tailed alternatives. A two tailed test looks for any difference. A left tailed test checks whether sample one is lower. A right tailed test checks whether sample one is higher. These choices change the p value and decision rule.
The z score measures distance from the null difference. It uses standard error as the measuring unit. A large absolute z score means the sample difference is unusual under the null. The p value then shows how unusual the result is.
Confidence intervals add another view. They estimate a likely range for the true difference. If a two sided interval excludes the null difference, it usually matches a significant two tailed test. Wider intervals show more uncertainty.
This calculator also reports an effect size. It standardizes the observed difference. This helps compare results across different measurement units. A statistically significant result may still be small in practical terms. Effect size helps reveal that gap.
Use the output with context. Check data quality before trusting the result. Confirm that samples are unrelated unless your design requires pairing. A paired design needs a different method. Also avoid using the z test when population deviations are unknown and samples are small. In that case, a two sample t test is usually more suitable.
The example table shows common inputs and outputs. It helps users verify the flow. The CSV and PDF buttons make reports easier to save. They are useful for class work, dashboards, and repeated analyses.
Keep every input in the same unit. Means and deviations must match. Sample counts must be positive whole numbers. Rounding may slightly change values, but not the main conclusion.