Statistical procedures use ODS Graphics to create graphs as part of their output. ODS Graphics is described in detail in Chapter 24, Statistical Graphics Using ODS.
Before you create graphs, ODS Graphics must be enabled (for example, by specifying the ODS GRAPHICS ON statement). For more information about enabling and disabling ODS Graphics, see the section Enabling and Disabling ODS Graphics in Chapter 24, Statistical Graphics Using ODS.
The overall appearance of graphs is controlled by ODS styles. Styles and other aspects of using ODS Graphics are discussed in the section A Primer on ODS Statistical Graphics in Chapter 24, Statistical Graphics Using ODS.
You must also specify the options in the PROC LOGISTIC statement that are indicated in Table 18.
When ODS Graphics is enabled, then the EFFECT, EFFECTPLOT, ESTIMATE, LSMEANS, LSMESTIMATE, and SLICE statements can produce plots that are associated with their analyses. For information about these plots, see the corresponding sections of Chapter 20, Shared Concepts and Topics.
PROC LOGISTIC assigns a name to each graph it creates using ODS. You can use these names to reference the graphs when using ODS. The names are listed in Table 18.
Table 18: Graphs Produced by PROC LOGISTIC
| ODS Graph Name | Plot Description | Statement or Option | |
|---|---|---|---|
| CalibrationPlot | Panel of calibration plots for polytomous response | PLOTS=CALIBRATION or MODEL / GOF |
|
| Calibration plot for a single polytomous response level | PLOTS=CALIBRATION(UNPACK) | ||
| Calibration plot for binary response | PLOTS=CALIBRATION or MODEL / GOF |
||
| DfBetasPlot | Panel of dfbetas by case number | PLOTS=DFBETAS or MODEL / INFLUENCE or IPLOTS |
|
| Effect dfbetas by case number | PLOTS=DFBETAS(UNPACK) | ||
| DPCPlot | Difchisq and/or difdev by predicted probability by CI displacement C | PLOTS=DPC | |
| EffectPlot | Predicted probability | PLOTS=EFFECT | |
| InfluencePlots | Panel of influence statistics by case number | PLOTS=INFLUENCE or MODEL / INFLUENCE or IPLOTS |
|
| CBarPlot | CI displacement Cbar by case number | PLOTS=INFLUENCE(UNPACK) | |
| CPlot | CI displacement C by case number | PLOTS=INFLUENCE(UNPACK) | |
| DevianceResidualPlot | Deviance residual by case number | PLOTS=INFLUENCE(UNPACK) | |
| DifChisqPlot | Difchisq by case number | PLOTS=INFLUENCE(UNPACK) | |
| DifDeviancePlot | Difdev by case number | PLOTS=INFLUENCE(UNPACK) | |
| LeveragePlot | Hat diagonal by case number | PLOTS=INFLUENCE(UNPACK) | |
| LikelihoodResidualPlot | Likelihood residual by case number | PLOTS=INFLUENCE(UNPACK STDRES) | |
| PearsonResidualPlot | Pearson chi-square residual by case number | PLOTS=INFLUENCE(UNPACK) | |
| StdDevianceResidualPlot | Standardized deviance residual by case number | PLOTS=INFLUENCE(UNPACK STDRES) | |
| StdPearsonResidualPlot | Standardized Pearson chi-square residual by case number | PLOTS=INFLUENCE(UNPACK STDRES) | |
| LeveragePlots | Panel of influence statistics by leverage | PLOTS=LEVERAGE | |
| LeverageCPlot | CI displacement C by leverage | PLOTS=LEVERAGE(UNPACK) | |
| LeverageDifChisqPlot | Difchisq by leverage | PLOTS=LEVERAGE(UNPACK) | |
| LeverageDifDevPlot | Difdev by leverage | PLOTS=LEVERAGE(UNPACK) | |
| LeveragePhatPlot | Predicted probability by leverage | PLOTS=LEVERAGE(UNPACK) | |
| ORPlot | Odds ratios | Default or PLOTS=ODDSRATIO and MODEL / CLODDS= or ODDSRATIO |
|
| PhatPlots | Panel of influence by predicted probability | PLOTS=PHAT | |
| PhatCPlot | CI displacement C by predicted probability | PLOTS=PHAT(UNPACK) | |
| PhatDifChisqPlot | Difchisq by predicted probability | PLOTS=PHAT(UNPACK) | |
| PhatDifDevPlot | Difdev by predicted probability | PLOTS=PHAT(UNPACK) | |
| PhatLeveragePlot | Leverage by predicted probability | PLOTS=PHAT(UNPACK) | |
| PRCurve | Precision-recall curve | PLOTS=PR | |
| PROverlay | PR curves for comparisons | PLOTS=PR and MODEL / SELECTION= or ROC |
|
| ROCCurve | Receiver operating characteristics curve | PLOTS=ROC or MODEL / OUTROC= or SCORE OUTROC= or ROC |
|
| ROCOverlay | ROC curves for comparisons | PLOTS=ROC and MODEL / SELECTION= or ROC |
|