Specify the default settings for residual plots in ANOVA, Regression, DOE, and the Predictive Analytics Module

File > Options > Linear Models > Residual Plots

Specify default settings for residual plots in ANOVA, Regression, DOE, and the Linear Regression and Binary Logistic Regression analyses for the Predictive Analytics Module. The changes you make to the defaults remain until you change them again, even after you exit Minitab.

Note

To specify settings for residual plots in Time Series, in Minitab, choose File > Options > Individual Graphs > Residual Plots for Time Series.

Residuals for Plots

For more information, go to Which types of residuals are included in Minitab?.

Regular: Plot the raw residuals (also called regular residuals).
Standardized: Plot the standardized residuals.
Deleted: Plot the Studentized deleted residuals.

Residuals for Analyze Variability

For more information, go to Residuals in analyze variability.

Ratio: Plot the ratio residuals.
Ln: Plot the natural log (ln) residuals.
Standardized ln: Plot the standardized natural log (ln) residuals.

Residuals for Stability Study (random batch)

For more information, go to Marginal fits and residuals versus conditional fits and residuals.

Marginal regular: Plot the marginal residuals.
Marginal standardized: Plot the standardized marginal residuals.
Conditional regular: Plot the conditional residuals.
Conditional standardized: Plot the standardized conditional residuals.

Residuals for Orthogonal Regression

Regular: Plot the raw residuals (also called regular residuals).
Standardized: Plot the standardized residuals.

Residuals for Mixed Effects Model

For more information, go to Marginal fits and residuals versus conditional fits and residuals.

Conditional regular: Conditional residuals are the difference between the conditional fits and the observed values in the sample data. Use the conditional residuals to check the normality of the error term.
Conditional standardized: Plot the standardized versions of the conditional residuals. If an observation has a standardized residual greater than 2, it may be an outlier in your data.
Marginal regular: Marginal residuals are the difference between the marginal fits and the observed values in the sample data. Use marginal residuals to evaluate whether the marginal equations can represent the mean responses of y well at different levels of the fixed effect terms.
Marginal standardized: Plot the standardized versions of the marginal residuals. If an observation has a standardized residual greater than 2, it may be an outlier in your data.

Residual Plots

Individual plots: Display selected graphs separately.
Four in one: Display a histogram of residuals, a normal probability plot of the residuals, a plot of residuals versus fits, and a plot of residuals versus order in a single layout.

When Making Individual Plots

For more information, go to Residual plots in Minitab.

Histogram of residuals: Display a histogram of the residuals.
Normal plot of residuals: Display a normal probability plot of the residuals.
Residuals versus fits: Plot the residuals versus the fitted values.
Residuals versus order: Plot the residuals versus the order of the data. The row number for each data point is shown on the x-axis (for example, 1 2 3 4... n).

Include Anderson-Darling test with normal plot

Display the Anderson-Darling statistic on the normal probability plot of the residuals. The statistic is displayed only for models that have three or more degrees of freedom for error. For more information, go to The Anderson-Darling statistic.