Select the option that best describes your data.
Complete the following steps if your response data for all groups or factor levels are in one column.
Complete the following steps if the response data for each group are in different columns. If you have one categorical factor, each column is a level of that factor. If you have more than one categorical factor, each column is a group that is a combination of factor levels from all factors.
Enter a confidence level for the Bonferroni simultaneous confidence intervals. Usually, a simultaneous confidence level of 95% works well.
The simultaneous confidence level is the percentage of times that a set of confidence intervals includes the true standard deviations for all group comparisons, if you repeat the study multiple times. A 95% simultaneous confidence level indicates that, if you perform the study 100 times, the entire set of confidence intervals contains the population standard deviations for all groups in 95 of the studies.
For more information, go to Understanding individual and simultaneous confidence levels in multiple comparisons and What is the Bonferroni method?.
If you know that your data follow a normal distribution, select Use test and confidence intervals based on normal distribution to use Bartlett's test rather than the multiple comparisons test and Levene's test. If there are only 2 groups, the F-test is used instead of Bartlett's test.
The F-test and Bartlett's test are accurate only for normally distributed data. Any departure from normality can cause these tests to provide inaccurate results.