Comparing Groups

The GLM Procedure

Comparing Groups

An important task in analyzing data with classification effects is to estimate the typical response for each level of a given effect; often, you also want to compare these estimates to determine which levels are equivalent in terms of the response. You can perform this task in two ways with the GLM procedure: with direct, arithmetic group means; and with so-called least-squares means (LS-means).

Means Versus LS-Means

Multiple Comparisons

Simple Effects

Homogeneity of Variance in One-Way Models

Weighted Means

Construction of Least-Squares Means

Chapter Contents
Previous
Next
Top