Generalized Linear Model (GLM) Unique Features - Tests of Assumptions, Residual Statistics
After fitting a particular model, it is always extremely important to carefully inspect the results with regard to any serious violations of assumptions for the respective statistical tests and procedures. STATISTICA GLM includes a large number of options to aid in this task (see the Assumptions tab on the More Results dialog), including plots of means versus standard deviations, and various tests of the homogeneity of variances. Also, you can easily check for outliers by computing the extended list of predicted value and residual statistics (see the Residuals tab on the Results dialog), and sort the observations by a chosen residual statistic (e.g., the Mahalanobis distance, deleted residual value, leverage value etc.). A large number of options are also available to produce normal probability plots, histograms, or scatterplots of any of the predicted value or residual statistics, as well as variables that are not included in the model (e.g., for partial correlation plots).
Some Unique Features and Facilities of GLM