File > Options > Linear Models > Display of Results
Specify the tables to display by default and whether to display the simple tables or the expanded tables. The changes you make to the defaults remain until you change them again, even after you exit Minitab.
Display of results
Simple tables: Display the simpler version of tables.
Expanded tables: Display the expanded versions of the ANOVA or Deviance, Coefficients, Model Summary, and Fits and Diagnostics tables.
Display of results for regression
Basic tables: Display tables that are consistent with Release 16 regression.
Simple tables: Display the simpler version of tables.
Expanded tables: Display the expanded versions of the ANOVA or Deviance, Coefficients, Model Summary, and Fits and Diagnostics tables.
Method table
Display a table that summarizes non-default settings.
Analysis of variance/deviance
Display the ANOVA table or Deviance table. ANOVA tables are in the output for Fit Regression Model, Fit General Linear Model, and DOE analyses. Deviance tables are in the output for Fit Binary Logistic Model and Fit Poisson Model.
Model summary
Display statistics that evaluate model fit. These statistics for Fit Regression Model, Fit General Linear Model, and DOE Analyses include R2. The statistics for Fit Binary Logistic Model and Fit Poisson Model include deviance R2 and Akaike information criterion.
Coefficients
Display the coefficients, effects, and p-values.
Default coefficients: Display all linearly independent coefficients.
Full set of coefficients: Display coefficients for all levels of the categorical factor, including the final level, which is linearly dependent.
Equation
Separate equation for each set of categorical predictor levels: Display a separate equation for each combination of factor levels.
Single equation: Display one equation that includes all levels of all factors.
Fits and diagnostics
Only for unusual observations: Display fits and diagnostics for only the unusual observations.
For all observations: Display fits and diagnostics for all observations.
Confidence level for all intervals
Specify the confidence level. One minus the confidence level is the significance level for the effects plots in DOE analyses.
Use rounded values for Box-Cox transformations when possible
Round the optimal lambda (λ) to the nearest half when you have Minitab search for an optimal value.
