Other common assumptions
For independent t-tests and ANOVA
Homogeneity of variances: Levene’s test
Use: Used to test the equality of variances when comparing the means of independent groups e.g. Independent t-tests and ANOVA.
Note: The violation of this assumption is more serious than violation of the assumption of normality but both t-tests and ANOVA are fairly robust to deviations from this assumption. There are alternative tests within the t-test and ANOVA menus to deal with violations of this assumption.
Interpretation:
If the p-value is less than 0.05 reject H0 and conclude that the assumption of equal variances has not been met.
For repeated measures ANOVA
Sphericity: Mauchly’s test
Use: Tests for sphericity - a measure of whether variances of the differences between all repeated measures are all equal. If the assumption is not met, the F-statistic is positively biased leading to an increased risk of a type 1 error.
Interpretation:
Significant when p-value < 0.05 meaning there are significant differences between the variance of differences, i.e. condition of sphericity is not met. If the assumption is not met, use the Greenhouse-Geisser correction to the degrees of freedom which appears in the standard output.
Independent observations
For most tests, it is assumed that the observations are independent. That is the results for one subject* are not affected by another. Examples of data which is not independent are repeated measures on the same subject (use the specific tests for this type of experiment) and observations over time (check the Durbin Watson test for regression). Another situation where observations are not independent is when subjects are nested within groups with a common influence e.g. children within classes who may be influenced by the teacher (use multilevel modelling to include class as an extra RANDOM factor). Time series analysis (which allows for non-independent measurements over time) and multilevel modelling are beyond the scope of most students.
*The subject is the unit of interest which could be a person, an observation, a day etc.