The Test of Equal Variances conducts hypothesis tests for the equality variances using F, Bartlett's and Levene's tests. The F Test is performed in place of the Bartlett's test when there are only two levels. Many statistical procedures like ANOVA and 2-Sample t-test assumes that samples are taken from populations with equal variances. This procedure can be used to valid this assumption.
| Null Hypothesis, H0 | Alternate Hypothesis, H1 |
| s12 = s22 = ... = si2 | s12 <> s22 <> ... <> si2 |
where si2 are the variances of population i
At the Excel Menu (For Excel 2007, go to Add-ins first)
Choose ProcessMA > Statistics > ANOVA > Test of Equal Variances
In Variable, select the column containing the response data (Numeric)
In Factor, select the column containing factor levels (>=2 levels)
In Confidence Level, enter the desired confidence level for the confidence interval (Numeric, >0 & <1)
Check F-Test or Barlett's, if you want to perform the f-test (factor with 2 levels) or Barlett's test
Check Levene's, if you want to perform the Levene's test
Click OK
A company makes steel bolts using four different machines. You want to assess if the variation in dimensions of the steel bolts made are the same for the different machines. You randomly selected 50 steel bolts made by each machine.
Open data worksheet by choosing ProcessMA > Tools > Data
Choose ProcessMA > Statistics > ANOVA > Test of Equal Variances
In Variable, select B - Dimension
In Subgroup, select C - Machine
Check F-Test or Barlett's
Check Levene's
The p-value of the tests is 0.3735 and 0.401 for Barlett’s and Levene’s tests respectively. For a desired a of 0.05, since p > a, we fail to reject H0. Therefore, we conclude that there is no significant evidence that the variances are different.
Copyright © ProcessMA