Residual Analysis - Outliers Tab

Multiple Regression - Computational Approach

Select the Outliers tab of the Residual Analysis dialog to access options to review outliers. All residual plots and spreadsheets are unlimited/user-limited as defined by the Maximum number of rows (cases) in a single results Spreadsheet or Graph box on the Residual Analysis - Advanced tab. Note that when Pairwise deletion is selected in the MD deletion group box in the Startup Panel, the program will substitute any missing values with the respective means in the computations for predicted and residual values (and related statistics).

Casewise plot of outliers

Click the Casewise plot of outliers button to display a spreadsheet in which the selected values are plotted in the left-most column. At the same time, all residual statistics are computed and can be reviewed (in the subsequent columns of the spreadsheet). Thus, this option allows you to identify outliers in even very large data files, since only the most extreme cases are plotted. Cases which have been chosen in the Type of outlier group box are used in this plot.

Type of outlier

Select the Type of outlier that you want to use in the Casewise plot of outliers in this group box.

Standard residual (> 2*sigma)

Select the Standard residual option button to plot only cases for which the absolute standard residual value is greater than 2 times sigma.

Plot 100 most extreme cases

Select from the Plot 100 most extreme cases option buttons to plot the 100 most extreme cases, sorted in descending order of magnitude, of either the Standard predicted, Standard residuals, Mahalanobis distances, Deleted residuals, or Cook's distances values (for explanations of these statistics see Residuals and Predicted Values).