Example of Test for Equal Variances

A safety analyst wants to compare the variability in steering correction times for experienced and inexperienced drivers on three types of roads: paved, gravel, and dirt. The analyst records the time in seconds that each driver uses to make steering corrections on each type of road.

  1. Open the sample data, RoadConditions.MTW.
  2. Choose Stat > ANOVA > Test for Equal Variances.
  3. Select Response data are in one column for all factor levels.
  4. In Response, enter 'Correction Time'.
  5. In Factors, enter Experience and RoadType.
  6. Click OK.

Interpret the results

In this summary plot, the p-values of 0.943 and 0.830 are greater than the common significance level of 0.05. None of the differences between the groups are statistically significant, and all the comparison intervals overlap.


Null hypothesisAll variances are equal
Alternative hypothesisAt least one variance is different
Significance levelα = 0.05

95% Bonferroni Confidence Intervals for Standard Deviations

AdvancedDirt45.09902(0.45310, 168.555)
AdvancedGravel44.16333(0.42041, 121.108)
AdvancedPaved43.87298(0.31299, 140.776)
BeginnerDirt46.05530(1.01104, 106.529)
BeginnerGravel44.76095(0.89964, 74.009)
BeginnerPaved45.88784(0.52320, 194.630)
Individual confidence level = 99.1667%


Multiple comparisons0.943