A z-test is a statistical test used to compare sample and population means when the population variance is known and the sample size is large.
What Is a z-Test?
A z-Test is a type of statistical test in statistics. Researchers use it when they want to compare a sample mean to a known population mean. This test is useful when the population variance is known and the sample size is large, usually greater than 30.
The name z-Test comes from the z-Score, which is a value from the standard normal distribution. The z-Score tells us how far our sample mean is from the population mean in terms of standard deviations. If the sample mean is far enough from the population mean, we might conclude that there’s a significant difference.
In social science research, z-Tests help test theories, evaluate programs, or check whether observed patterns could have occurred by chance.
When to Use a z-Test
Known Population Standard Deviation
A z-Test is only appropriate when you know the population’s standard deviation. This is a rare situation in many social science settings, but it can happen when previous studies have established the population parameters very well.
Large Sample Size
Researchers generally use the z-Test for large samples—typically when the sample size is 30 or more. This is because the Central Limit Theorem tells us that the sampling distribution of the mean will be approximately normal in large samples, even if the original population is not.
Testing One Sample Against a Known Population Mean
Use a z-Test when you have one group of people (a sample) and you want to compare their average score on something to a known average in the population. For example, if you want to compare the average test scores of 100 students from one school to the national average, and you know the population standard deviation, you can use a z-Test.
How the z-Test Works
Step 1: State the Hypotheses
You start by writing two hypotheses:
- Null Hypotheses (H₀): There is no difference between the sample mean and the population mean.
- Alternative Hypothesis (H₁): There is a difference between the sample mean and the population mean.
Depending on your research objective, the test can be:
- Two-tailed Test: Tests for any difference (higher or lower).
- One-tailed Test: Tests for a specific direction (either higher or lower).
Step 2: Set the Significance Level
Most researchers use an Alpha Level of 0.05. This means you’re willing to accept a 5% chance of rejecting the null hypothesis when it’s actually true.
Step 3: Calculate the z-Score
The formula for the z-Score is:
z = (sample mean – population mean) / (population standard deviation / square root of sample size)
This formula tells you how many standard errors your sample mean is away from the population mean.
Step 4: Find the Critical Value
Using a z-Score table, you find the critical value that matches your chosen Alpha Level. For a 0.05 Alpha Level in a Two-tailed Test, the critical values are -1.96 and 1.96.
Step 5: Make a Decision
Compare your calculated z-Score to the critical value. If it falls beyond the critical value (either below -1.96 or above 1.96 in a Two-tailed Test), you reject the Null Hypothesis.
Example from Education Research
Let’s say researchers want to know if a new teaching method changes students’ math scores. The national average math score is 500, and the population standard deviation is known to be 100. A group of 64 students who learned with the new method had an average score of 520.
We can use a z-Test:
- Sample mean = 520
- Population mean = 500
- Population standard deviation = 100
- Sample size = 64
z = (520 – 500) / (100 / √64) = 20 / (100 / 8) = 20 / 12.5 = 1.6
The calculated z-Score is 1.6. The critical value for a Two-tailed Test at Alpha Level = 0.05 is ±1.96. Since 1.6 does not exceed 1.96, the result is not statistically significant.
So, the researchers would fail to reject the Null Hypothesis. That means there’s not enough evidence to say the new method makes a difference.
z-Test vs t-Test
A common question in social science research is whether to use a z-Test or a t-Test. Here’s the key difference:
- Use a z-Test when you know the population standard deviation and have a large sample.
- Use a t-Test when the population standard deviation is unknown and/or the sample size is small.
In practice, social scientists often use the t-Test more frequently, because it’s rare to know the population standard deviation. However, the z-Test remains a foundational concept in statistical tests and helps build understanding of hypothesis testing.
Variations of the z-Test
One-Sample z-Test
This is the most common version. It tests whether one sample mean is significantly different from a known population mean.
Two-Sample z-Test
Used to compare two sample means from different groups when population variances are known. For example, comparing average test scores from two different cities where both populations’ standard deviations are known.
z-Test for Proportions
Instead of means, this version compares proportions. For example, a political scientist might want to test if the proportion of voters who support a policy in a sample differs from the known proportion in the population.
Strengths of the z-Test
- Easy to calculate and understand
- Useful for large samples
- Helpful in teaching the basics of hypothesis testing
- Based on the normal distribution, which is well-understood and widely used
Weaknesses of the z-Test
- Not realistic in many social science contexts, where population standard deviations are rarely known
- Assumes normal distribution of the sample mean, which might not hold in smaller samples
- Less flexible than the t-Test for smaller sample sizes
Common Mistakes to Avoid
Assuming You Can Use a z-Test Without Knowing the Population Standard Deviation
One of the biggest errors is using a z-Test without meeting this condition. If you’re unsure about the population standard deviation, use a t-Test instead.
Using a z-Test with a Small Sample
Even if you know the population standard deviation, it’s still risky to use a z-Test with a small sample (under 30). Small samples can have more variability, which can lead to inaccurate conclusions.
Confusing z-Scores and p-Values
The z-Score tells you how far away the sample mean is from the population mean. The p-Value tells you how likely it is to get a result that extreme by chance. These are related but not the same.
Why the z-Test Matters in Social Science Research
In social sciences, researchers often want to know if what they observe in a sample can be trusted as true for a larger group. The z-Test is one tool that helps answer this question. When used properly, it allows researchers to make clear, evidence-based claims about group differences.
Even though the z-Test is not used as often as other statistical tests like the t-Test or ANOVA, it’s an important building block in understanding statistical significance. It teaches the logic behind hypothesis testing and the use of probability to make decisions about data.
Researchers in psychology, education, political science, and sociology all benefit from understanding how and when to apply this test. Whether evaluating survey responses, testing the impact of a new program, or comparing group behaviors, the z-Test remains part of the foundation of good statistical practice.
Summary
The z-Test is a basic statistical test for testing differences between sample and population means when the population variance is known. It works best with large samples and is based on the standard normal distribution. While not always practical in real-world research due to its strict assumptions, it helps researchers understand the fundamentals of hypothesis testing and statistical significance.
Glossary Return to Doc's Research Glossary
Last Modified: 04/03/2025