# Mixed ANOVA

#### Nin

##### New Member
Using SPSS, I've run a 2 (sex: male, female) X 2 (age: young, old) X 3 (time1, time2, time3) a mixed analysis of variance, with time as the repeated measures variable/dependent variable.
I found a significant main effect for gender, but I want to find where the gender differences on the time 1, 2, 3 variables are.
I've been told I need to run 3 separate univariate ANOVAs and to change the alpha level to p=.02 using the Bonferroni criterion (.05/3=.02 alpha level). Is this correct? If so, how would I go about doing such an analysis? Also what happens if my "homogeneity of variances" assumption is violated in the univariate ANOVAs?

##### New Member
Did anyone ever answer this? Just curious.

#### Dragan

##### Super Moderator
Using SPSS, I've run a 2 (***: male, female) X 2 (age: young, old) X 3 (time1, time2, time3) a mixed analysis of variance, with time as the repeated measures variable/dependent variable.
I found a significant main effect for gender, but I want to find where the gender differences on the time 1, 2, 3 variables are.
I've been told I need to run 3 separate univariate ANOVAs and to change the alpha level to p=.02 using the Bonferroni criterion (.05/3=.02 alpha level). Is this correct? If so, how would I go about doing such an analysis? Also what happens if my "homogeneity of variances" assumption is violated in the univariate ANOVAs?

Did you find a significant difference for the main effect AGE?