Analysis of Variance (ANOVA) is a hypothesis testing procedure that tests whether two or more means are significantly different from each other.
This article describes how to go create a Table of Means - a table showing the mean of an Outcome variable (perception of Coke as a feminine brand), by two other variables, where one is shown in the Rows (Age) and the other in the Columns (Gender).
- A Numeric variable to use as an Outcome variable.
- At least two Categorical variables containing two or more groups to be used for Rows and Columns.
If the Outcome is not numeric and if the Rows and Columns are not categorical, they are coerced to such types.
- In the Table menu select Specialty > Table of Means.
- In the object inspector go to the Inputs tab.
- In the Outcome menu select the predictor variable.
- Select the variable to show in rows from the Rows list.
- Select the variable to show in columns from the Columns list.
- OPTIONAL: Select the desired multiple comparisons correction from the Correction list.
- OPTIONAL: To compute standard errors that are robust to violations of the assumption of constant variance (i.e., heteroscedasticity) select Robust standard errors.
- OPTIONAL: Select Variable names to display Variable names in the output instead of labels.