Stat > Basic Statistics > 2 Variances > Options
Specify the type of ratio, the confidence level, the hypothesized ratio, and the alternative hypothesis for the test. You can also choose to use the F-test rather than Levene's and Bonett's test.
Ratio:
(sample 1 standard deviation) / (sample 2 standard deviation): Choose to test the ratio of the standard deviations.
(sample 1 variance) / (sample 2 variance): Choose to test the ratio of the variances.
Confidence level: Enter a confidence level for the confidence interval. Enter any number between 0 and 100. The default is 95.
The significance level for the tests (also called alpha or a) is also determined by the confidence level. The significance level = 1 - (confidence level / 100). For example, if you choose 95 as the confidence level, the significance level for the tests is 1 - (95 / 100) = 0.05.
Hypothesized ratio: Enter the hypothesized value for the ratio. Use the default value of 1 to test the equality of two population variances or standard deviations.
Alternative hypothesis: Choose the alternative hypothesis that you want to test.
Use test and confidence intervals based on normal distribution: Check to use the F-test rather than Levene's and Bonett's test. The F-test is accurate only for normally distributed data. Any departure from normality can cause the F-test to yield inaccurate results.