Bartlett's Test Calculator
Bartlett's test is used to test the assumption that variances are equal (homogeneous) across groups. For help in using this calculator, read the Frequently-Asked Questions or review the Sample Problem.
To learn more about Bartlett's test, read Stat Trek's tutorial on Bartlett's test.
Frequently-Asked Questions
Instructions: To find the answer to a frequently-asked question, simply click on the question.
How does Bartlett's test work?
What steps (computations) are required to execute Bartlett's test?
What should I enter in the field for number of groups?
What should I enter for significance level?
What should I enter for sample size?
What should I enter for variance?
What is degrees of freedom?
What is the test statistic (T)?
What is the P-value?
How does the calculator test hypotheses?
Sample Problems
Problem 1
The table below shows sample data and variance for five groups. How would you test the assumption that variances are equal across groups?
Group 1 | Group 2 | Group 3 | Group 4 | Group 5 |
---|---|---|---|---|
Sample Data | ||||
1 2 3 4 5 |
1 3 5 7 9 |
1 4 7 10 13 |
1 5 9 13 17 |
1 6 11 16 21 |
Variance | ||||
2.5 | 10 | 22.5 | 40 | 62.5 |
One option would be to use Stat Trek's Bartlett's Test Calculator. Simply, take the following steps:
- Enter the number of groups (5).
- Enter the significance level. For this problem, we'll use 0.05.
- For each group, enter sample size. In this example, the sample size is 5 for each group.
- For each group, enter a sample estimate of group variance.
Then, click the Calculate button to produce the output shown below:


From the calculator, we see that the test statistic (T) is 8.91505. Assuming equal variances in groups and given a significance level of 0.05, the probability of observing a test statistic (T) bigger than 8.91505 is given by the P-value. Since the P-value (0.06326) is bigger than the significance level (0.05), we cannot reject the null hypothesis of equal variances across groups.
Note: To see the hand calculations required to solve this problem, go to Bartlett's Test for Homogeneity of Variance: Example 1.