Running the analysis (generalized linear mixed models)
- To
fit a linear mixed model, from the menus choose:
Figure 1. Data Structure tab 
- Select School (school), Classroom (classroom), and Student ID (student_id) as subject fields.
- Click Fields & Effects.
Figure 2. Target settings 
- On the Target settings, confirm that Post-test (posttest) is selected as the target. Post-test (posttest) has a predefined role as a target, so it is automatically selected as the target by default.
- Confirm that Linear model is selected in the Target Distribution and Relationship (Link) with the Linear Model group. The linear model assumes a normal distribution for the target and uses an identity link function.
- Click Fixed Effects.
Figure 3. Fixed Effects settings 
- Confirm that Use custom inputs is selected.
- Select School setting, School
type, Teaching method, Number of students in the classroom, Gender, Reduced/Free lunch, and Pre-test, and drag to the Main drop zone to create the main effects.
The fields with categorical (flag, nominal, or ordinal) measurement level are treated as factors by the procedure and those with continuous (scale) measurement level are treated as covariates.
- Click Random
Effects.
Figure 4. Random Effects settings 
- Confirm that two intercept-only random effect
subject blocks exist; one with school as the subject field and one with school*classroom as the subject field. The procedure automatically creates a Random
Effect block for each subject beyond the innermost subject.
The first block should account for correlation between classrooms within the same school. The second block should account for correlation between students within the same classroom.
- Click Run.