Check for outliers, equal variance, normality, and model validity

B. Check for equal variance.

At the bottom of the output, you will see something like:                                      

This gives an equal variance diagnostic checks.

 Verify that the stddev_y values are within 5-fold of each other, and that the Levene P is greater than 0.05.

    If so, treatment variances are sufficiently equal for the standard ANOVA to be valid.

    Even if the Levene P is less than 0.05, there still should not be any problem.

    If stddev_y values are not within 5-fold of each other and the Levene P is less than 0.05, then you will
      need to consider transformations, but first see next screen to check normality.

In the above example, the stddev_y values are within 5-fold of each other, and the Levene P is greater than 0.05. Therefore, you do have equal variance across treatments.

In the example below, there is unequal variance:

Note that even though the Levene P is above 0.05, since the stddev_y values differ by more than five-fold, there is unequal variance. More weight is given to the standard deviations in detecting unequal variance.

A transformation will hopefully correct this problem. However, first you should go to Step C to check for normality, as information there will help in choosing a transformation.

 next >> ( Step C: Check for Normality )