General Linear Model (GLM) is used to perform univariate analysis of variance with balanced and unbalanced designs and regression for the response variable.
1. Choose ProcessMA > Statistics > ANOVA > General Linear Model.
2. In Response, select the column containing the response values.
3. In Factors, select the columns containing variables in the model that are factors.
4. In Covariates, select the columns containing variables in the model that are covariates
5. In Model, select or enter the terms to be included in the model.
· Use * to indicate interaction - Example A*B is the interaction of factors A & B.
· Use () to indicate nesting - Examples B(A) means B is nested within A. Note that only 1 factor can be in the parenthesis.
6. Check Residual plots, to display different plots of the residuals.
7. Click OK.
Note To select a column of data into a textbox, double-click on any of the column names shown in the list on the left of the dialog box while in the textbox.
Response: Numeric.
Factors: Text or Numeric; Factors must have at least 2 levels; Must have equal number of data points as the response.
Covariates: Numeric; Cannot be constant; Must have equal number of data points as the response.
Model: Column names.
You conducted an experiment to study the effect of material type and blade size on the wind generated by an electric fan. There are 3 types of materials and 3 blade sizes. The material type is a fixed factor and the blade size is a covariate.
1. Open worksheet ProcessMA > Tools > Data Files > Stat.xls.
2. Choose ProcessMA > Statistics > ANOVA > General Linear Model.
3. In Response, select S – Wind.
4. In Factors, select T – Material.
5. In Covariates, select U – BladeSize.
6. In Model, enter Material, BladeSize, Material*BladeSize.
7. Click OK.
Interpretation
From the ANOVA table, all the p-values are less than 0.005 which indicate that there are significant evidences on the effects. The R-sq shows that the model explains 89.7% of the variance in wind.