# ROC Analysis: Display

You can specify the following display settings for your ROC analysis:

- Plot
- Provides options for plotting the ROC and Precision-Recall curves.
- ROC Curve
- When selected, a ROC Curve chart displays in the output. Select With diagonal reference line to draw a diagonal reference line on the ROC Curve chart.
- Precision-Recall Curve
- When selected, a Precision-Recall Curve chart displays in the output. Precision-Recall Curves tend to be more informative when the observed data samples are highly skewed and provide an alternative to ROC Curves for data with a large skew in the class distribution. The default Interpolate along the true positives setting makes the stepwise interpolation along the true positives. The Interpolate along the false positives setting makes the stepwise interpolation along the false positives.
- Overall model quality
- The setting controls whether or not a bar chart is created to display the value of the lower bound of the confidence interval of the estimated AUC. By default, the setting is not selected, which suppresses the bar chart.

- Provides options for defining the output for the corresponding statistics.
- Standard error and confidence interval
- The setting controls which statistics display in the "Area Under the Curve" table. When the setting is not selected, only the estimated AUC displays. When the setting is selected, additional statistics display, including the standard error of the AUC, the asymptotic significance (2-tail), and the Asymptotic Confidence Interval bounds under the null hypothesis.
- Coordinate points of ROC Curve
- The setting controls the coordinate points of the ROC Curve, along with the cutoff values. When the setting is not selected, the output of coordinate points is suppressed. When the setting is selected, the pairs of Sensitivity and (1-Specificity) values are given with the cutoff values for each ROC Curve.
- Coordinate points of the Precision-Recall Curve
- The setting controls the coordinate points of the Precision-Recall Curve, along with the cutoff values. When the setting is not selected, the output of coordinate points is suppressed. When the setting is selected, the pairs of Precision and Recall values are given with the cutoff values for each Precision-Recall Curve.
- Classifier evaluation metrics
- The setting controls the display of the Classifier Evaluation Metrics table
in the output. The table shows how well a classification model fits the data compared to a random
assignment and provides the following information:
- The user-specified test variables
- Group information
- Gini Index (the Gini index is 2*AUC - 1, where AUC is the area under the ROC curve)
- Max K-S and Cutoff values

## Defining display options

This feature requires the Statistics Base option.

- From the menus choose:
- Click Display.
- Define the display options.