Enter your data for Factorial Plots

Complete the following steps to display the factorial plots, which include main effects plots and interaction plots.

This dialog box varies by the type of model that you used to fit the data.

Models from the Predictive Analytics Module

  1. Go to the results for a Linear Regression model or for a Binary Logistic Regression model, then select Factorial Plots.
  2. Under Variables to Include in Plots, move the variables that you want to include in the plot from the Available list to the Selected list. If an expected variable does not appear in either list, that term was not included in the model.
    • Available: Lists all of the variables in your model that you can include in the plots.
    • Selected: Lists all of the variables that will be included in the plots. You can have up to 50 variables in the Selected list.
  3. From Terms to display, select the terms that you want to include in the factorial plots.
    • Only model terms: Display plots only for the terms that are in the model. All plots display the fitted values.
    • All terms: Display plots for all terms that include variables that are in the Selected list. Plots for terms that are not in the model display the data means, not the fitted means. For more information about the types of means, go to Data and fitted means.
    For example, assume that a model specifies Categorical 1 and Categorical 2 but not the two-way interaction between these variables. If you move both terms to Selected and select Only model terms, the interaction is not displayed. However, if you select All terms, the interaction plot for Categorical 1*Categorical 2 is displayed because both terms are selected.

Models from the Stat menu except mixture designs

  1. To perform this analysis in Minitab, go to the menu that you used to fit the model, then choose Factorial Plots. For example, if you fit a Poisson model, choose Stat > Regression > Poisson Regression > Factorial Plots.
  2. From Response, select a response variable.
    Note

    Only response variables with up-to-date models from the same analysis are in the list. If you do not see a response that you want, re-fit the model. For more information, go to Stored model overview.

  3. Under Variables to Include in Plots, move the variables that you want to include in the plot from the Available list to the Selected list. If an expected variable does not appear in either list, that term was not included in the model.
    • Available: Lists all of the variables in your model that you can include in the plots.
    • Selected: Lists all of the variables that will be included in the plots. You can have up to 50 variables in the Selected list.
  4. From Terms to display, select the terms that you want to include in the factorial plots.
    • Only model terms: Display plots only for the terms that are in the model. All plots display the fitted values.
    • All terms: Display plots for all terms that include variables that are in the Selected list. Plots for terms that are not in the model display the data means, not the fitted means. For more information about the types of means, go to Data and fitted means.
    For example, assume that a model specifies Categorical 1 and Categorical 2 but not the two-way interaction between these variables. If you move both terms to Selected and select Only model terms, the interaction is not displayed. However, if you select All terms, the interaction plot for Categorical 1*Categorical 2 is displayed because both terms are selected.

Mixture designs

For mixture designs, these plots display only data means.

  1. To display the main effects and interaction plots for a mixture design, choose Stat > DOE > Mixture > Factorial Plots.
  2. Select Main Effects Plot and/or Interaction Plot and then click the Setup buttons that correspond to the graphs that you selected.
    Note

    If you want to create a Cube Plot, go to Enter your data for Cube Plot.

  3. In Responses (optional), select at least one response variable.
  4. Under Process Variables to Include in Plots, move the variables that you want to include in the plot from the Available list to the Selected list. If an expected variable does not appear in either list, that term was not included in the model.
    • Available: Lists all of the variables in your model that you can include in the plots.
    • Selected: Lists all of the variables that will be included in the plots. You can have up to 7 process variables in the Selected list.