Model Fitting: Logistic Regression |
Plots Tab |
You can use the Plots tab to create plots that graphically display results of the analysis. (See Figure 23.4.) There are plots that help you to visualize the fit, the residuals, and various influence diagnostics.
Creating a plot often adds one or more variables to the data table. The following plots are available:
creates a line plot of the predicted probability versus the continuous explanatory variable. This plot is created only if the following conditions are satisfied:
There is exactly one continuous explanatory variable.
There are three or fewer classification variables.
There are 12 or fewer joint levels of the classification variables.
creates a line plot that shows the trade-off between sensitivity and specificity. Models that fit the data well correspond to a receiver operating characteristic (ROC) curve that has an area close to unity. A completely random predictor would produce an ROC curve that is close to the diagonal and has an area close to 0.5.
creates a scatter plot of the Pearson chi-square residuals versus the predicted probabilities.
creates a scatter plot of the deviance residuals versus the predicted probabilities.
creates a scatter plot of the deletion chi-square goodness-of-fit (DIFCHISQ) statistic versus the predicted probabilities.
creates a scatter plot of the deletion deviance (DIFDEV) statistic versus the predicted probabilities.
creates a scatter plot of the confidence interval displacement diagnostic () versus the predicted probabilities.
creates a scatter plot of the confidence interval displacement diagnostic () for each observation.
creates a scatter plot of the leverage statistic for each observation.
Copyright © SAS Institute, Inc. All Rights Reserved.