ABSTRACT
In experiments involving multiple independent variables and one dependent variable, the general linear model (GLM)
univariate analysis of variance
is usually used to answer questions about the effects of the independent variables on the dependent variable. The last example in Chapter 7 examined the effects of three independent variables (type of learning strategy, shock level, and difficulty of material) on the dependent variable of the number of errors made by each subject in learning one list of material. As the experiment involved only one dependent variable, the GLM univariate (2
×
×
2) analysis of variance was the appropriate test to use. However, if the experiment had required each subject to learn four different lists of material (instead of one list), the GLM univariate analysis would no longer be appropriate. This is because the dependent variable is no longer a single measure but four different scores obtained for each subject. Although the GLM univariate analysis of variance can be conducted separately for each of the four dependent variables, the
GLM multivariate analysis of variance
is more appropriate. Unlike univariate tests, GLM multivariate analysis takes into account the interrelation among dependent variables and analyzes the variables simultaneously.
