GLZ Results - Resid. 2 Tab

Select the Resid. 2 tab of the GLZ Results dialog box to access options to produce spreadsheets and plots of various predicted and residual statistics. For details regarding the computation and interpretation of these residual statistics, refer to McCullagh and Nelder, 1989.

Sample.

Analysis, Cross-validation, Both. Select the respective option button under Sample to specify which type of sample to base the predicted and residual statistics. You can display spreadsheets for all observations that were used to compute the current results (select Analysis), all observations that were not used to compute the current results, but have valid data for all predictor and dependent variables (select Cross-validation), or all observations in both the Analysis sample and the Cross-validation sample (select Both). If these options are not available, no cross-validation sample was specified on the Quick Specs Dialog - Advanced tab, or via the Sample keyword in the Analysis Syntax Editor.

Pred. & P. resid. Click the Pred. & P. resid button to produce a scatterplot of the predicted values vs. Pearson residuals.

Pred. & D. resid. Click the Pred. & D. resid button to produce a scatterplot of the predicted values vs. deviance residuals.

Obs. & P. resid. Click the Obs. & P. resid button to produce a scatterplot of the observed values vs. Pearson residuals.

Obs. & D. resid. Click the Obs. & D. resid button to produce a scatterplot of the observed values vs. deviance residuals.

Res. & P. resid. Click the Res. & P. resid button to produce a scatterplot of the raw residuals vs. Pearson residuals.

Res. & D. resid. Click the Res. & D. resid button to produce a scatterplot of the raw residuals vs. deviance residuals.

Pred. & leverage. Click the Pred. & leverage button to produce a scatterplot of the predicted values vs. leverage values.

Pred. & uwgt. lev. Click the Pred. & uwgt. lev. button to produce a scatterplot of the predicted values vs. unweighted leverage values.

Pred. & Diff. X2. Click the Pred. & Diff. X2 button to produce a scatterplot of the predicted values vs. differential Pearson Chi-square statistics.

Lev. & Diff. X2. Click the Lev. & Diff. X2 button to produce a scatterplot of the leverage values vs. differential Pearson Chi-square statistics.

Pred. & Diff. Dev. Click the Pred. & Diff. Dev. button to produce a scatterplot of the predicted values vs. differential deviance statistics.

Lev. & Diff. Dev. Click the Lev. & Diff. Dev. button to produce a scatterplot of the leverage values vs. differential deviance statistics.

Pred. & Cook D. Click the Pred. & Cook D button to produce a scatterplot of the predicted values vs. generalized Cook's distances.

Lev. & Cook D. Click the Lev. & Cook D button to produce a scatterplot of the leverage values vs. generalized Cook's distances.

Save basic resid. Click the Save basic resid button to display a standard variable selection dialog box, which is used to select variable(s) to be displayed together with the basic residual values. After you select the variable(s), a spreadsheet containing the specified variable(s) along with numerous residual statistics ( i.e., the raw residuals, Pearson residuals, deviance residuals, and scaled residuals) will be displayed in an individual window (regardless of the settings in the Options dialog box - Output Manager tab or the Analysis/Graph Output Manager dialog box). You can, however, add the spreadsheet to a workbook or report using the or buttons, respectively. Note that in order to save the spreadsheet, you must select the spreadsheet and select Save or Save As from the File menu. This is useful if you want to use the residual values for further analyses with other STATISTICA analyses.

Save predicted. Click the Save predicted button to display a standard variable selection dialog box, which is used to select variable(s) to be displayed together with the predicted values and related statistics. After you select the variable(s), a spreadsheet containing the specified variable(s) along with the predicted values and related statistics (i.e., the predicted values, observed responses, linear predictor values, and the confidence intervals for the predicted values) will be displayed in an individual window. See Save basic resid above for further details.

Save other resid. Click the Save other resid button to display a standard variable selection dialog box, which is used to select variable(s) to be displayed together with other residual values. After you select the variable(s), a spreadsheet containing the specified variable(s) along with numerous residual statistics (i.e., the studentized residual values, leverage values, studentized Pearson residuals, studentized deviance residuals, and likelihood residuals) will be displayed in an individual window. See Save basic resid above for further details.

Save obs. stat. Click the Save obs. stat button to display a standard variable selection dialog box, which is used to select variable(s) to be displayed together with observational statistics. After you select the variable(s), a spreadsheet containing the specified variable(s) along with numerous observational statistics (i.e., the differential Pearson Chi-square values, differential deviance values, and generalized Cook's distances) will be displayed in an individual window. See Save basic resid above for further details.

Aggregation. Select the Aggregation check box to compute the predicted values (and related statistics, e.g., residuals) in terms of predicted frequencies. In models with categorical response variables, predicted values (and related statistics, e.g., residuals) can be computed in terms of the raw data or for aggregated frequency counts. For example, in the Binomial case (see Distribution and link function), and for raw data, you can think of the response variable as having two possible values: 0 (zero) or 1. Accordingly, predicted values should be computed that fall in the range from 0 (zero) to 1 (e.g., classification probabilities). If the Aggregation check box is selected (also available on the Summary tab), STATISTICA will consider the aggregated (tabulated) data set. In that case, you can think of the response variable as a frequency count, reflecting the number of observations that fall into the respective categories. This is easiest imagined in the case where the predictors are also categorical in nature: The resulting aggregated data file would be a multi-way frequency table.

Fitted 2D Func. Click the Fitted 2D Func. (function & observed values) button to display a 2-dimensional graph of the observed values. This plot allows a 2-dimensional visual examination (i.e., qualitative evaluation) of the fit of the data to the model. Note that this button is not available when more than 1 covariate is specified because multiple predictors would result in larger dimensions.

See the Results for stepwise or best-subset regression and Overdispersion parameter for models with categorical responses notes in the GLZ Results topic for further information. See also, GLZ - Index.