The Bartlett test is more effective than Levene test when we do not reject the hypothesis of normality of the data.
Example: We consider a data set with one factor and several levels, as in the following table.
| Factor | Fiber Strenght |
| 15 | 7 |
| 15 | 7 |
| 15 | 15 |
| 15 | 11 |
| 15 | 9 |
| 20 | 12 |
| 20 | 17 |
| 20 | 12 |
| 20 | 18 |
| 20 | 18 |
| 25 | 14 |
| 25 | 18 |
| 25 | 18 |
| 25 | 19 |
| 25 | 19 |
| 30 | 19 |
| 30 | 25 |
| 30 | 22 |
| 30 | 19 |
| 30 | 23 |
| 35 | 7 |
| 35 | 10 |
| 35 | 11 |
| 35 | 15 |
| 35 | 11 |
click here to download the data
To use the tool Tests of Variance the user must follow these steps:
1. Access the menu:
Action
ANOVA
Tests of Variance
2. The following screen will be shown;
3. With the cursor in the field Factor, select the column that refers to the Factor (without the name of the column);
4. In Tests choose between the options Bartlett and Levene. In this case we will perform a Bartlett test;
5. With the cursor in the field Response Variable, select the column that refers to the Response Variable (without the name of the column);
6. In Show Results, choose one of the options. We suggest the option New Sheet, because Action does not have the undo command;
7. To finish, click Ok.
Results and Interpretation
Once the process is finishde, the following results will be shown:
We verity that the p-value of the test is bigger than the 5% significance level, so we accept the null hypothesis of equality of the variances.
