PROC LOGISTIC assigns a name to each table it creates. You can refer to the tables by these names when you use the Output Delivery System (ODS) to select tables and create output data sets. These names are listed in Table 17. For more information about ODS, see Chapter 23, Using the Output Delivery System.
The EFFECT, ESTIMATE, LSMEANS, LSMESTIMATE, MARGINS, and SLICE statements also create tables, which are not listed in Table 17. For information about these tables, see the corresponding sections of Chapter 20, Shared Concepts and Topics.
Table 17: ODS Tables Produced by PROC LOGISTIC
| ODS Table Name | Description | Statements | Options |
|---|---|---|---|
| Areas | Area under the curves | PROC LOGISTIC | ROCOPTIONS(AREA) (with ROC and PR curves) |
| Association | Association of predicted probabilities and observed responses | MODEL (without STRATA) |
Default |
| BestSubsets | Best subset selection | MODEL | SELECTION=SCORE |
| ClassFreq | Frequency breakdown of CLASS variables | PROC LOGISTIC | SIMPLE (with CLASS variables) |
| Classification | Classification table | MODEL | CTABLE |
| ClassLevelInfo | CLASS variable levels and design variables | MODEL | Default (with CLASS variables) |
| ClassWgt | Weight breakdown of CLASS variables | PROC LOGISTIC, WEIGHT |
SIMPLE (with CLASS variables) |
| CLOddsPL | Odds ratio estimates and profile-likelihood confidence intervals | MODEL | CLODDS=PL |
| CLOddsWald | Odds ratio estimates and Wald confidence intervals | MODEL | CLODDS=WALD |
| CLParmPL | Parameter estimates and profile-likelihood confidence intervals | MODEL | CLPARM=PL |
| CLParmWald | Parameter estimates and Wald confidence intervals | MODEL | CLPARM=WALD |
| ContrastCoeff | L matrix from CONTRAST | CONTRAST | E |
| ContrastEstimate | Estimates from CONTRAST | CONTRAST | ESTIMATE= |
| ContrastTest | Wald test for CONTRAST | CONTRAST | Default |
| ConvergenceStatus | Convergence status | MODEL | Default |
| CorrB | Estimated correlation matrix of parameter estimators | MODEL | CORRB |
| CovB | Estimated covariance matrix of parameter estimators | MODEL | COVB |
| CumulativeModelTest | Test of the cumulative model assumption | MODEL | Default with cumulative response |
| EffectInModel | Test effects in model | MODEL | SELECTION=S | B |
| EffectNotInModel | Test for effects not in model | MODEL | SELECTION=S | F |
| ExactOddsRatio | Exact odds ratios | EXACT | ESTIMATE=ODDS, ESTIMATE=BOTH |
| ExactParmEst | Parameter estimates | EXACT | ESTIMATE, ESTIMATE=PARM, ESTIMATE=BOTH |
| ExactTests | Conditional exact tests | EXACT | Default |
| FastElimination | Fast backward elimination | MODEL | SELECTION=B, FAST |
| FitStatistics | Model fit statistics | MODEL | Default |
| GlobalScore | Global score test | MODEL | NOFIT |
| GlobalTests | Test for global null hypothesis | MODEL | Default |
| GoodnessOfFit | Pearson and deviance goodness-of-fit tests | MODEL | SCALE, GOF |
| IndexPlots | Batch capture of the index plots | MODEL | IPLOTS |
| Influence | Regression diagnostics | MODEL | INFLUENCE |
| IterHistory | Iteration history | MODEL | ITPRINT |
| LackFitChiSq | Hosmer-Lemeshow chi-square test results | MODEL | LACKFIT, GOF |
| LackFitPartition | Partition for the Hosmer- Lemeshow test | MODEL | LACKFIT, GOF |
| LastGradient | Last evaluation of gradient | MODEL | ITPRINT |
| Linear | Linear combination | PROC LOGISTIC | Default |
| LogLikeChange | Final change in the log likelihood | MODEL | ITPRINT |
| ModelANOVA | Joint or Type 3 tests of effects | MODEL | Default (with CLASS variables) |
| ModelBuildingSummary | Summary of model building | MODEL | SELECTION=B | F | S |
| ModelInfo | Model information | PROC LOGISTIC | Default |
| NObs | Number of observations | PROC LOGISTIC | Default |
| OddsEst | Adjusted odds ratios | UNITS | Default |
| OddsRatios | Odds ratio estimates | MODEL | Default |
| OddsRatiosPL | Odds ratio estimates and PL confidence intervals | ODDSRATIOS | CL=PL |
| OddsRatiosWald | Odds ratio estimates and Wald confidence intervals | ODDSRATIOS | CL=WALD |
| ParameterEstimates | Maximum likelihood estimates of model parameters | MODEL | Default |
| ResidualChiSq | Residual chi-square | MODEL | SELECTION=F | B |
| ResponseProfile | Response profile | PROC LOGISTIC | Default |
| ROCAssociation | Association table for ROC models | ROC MODEL |
Default ROCCI |
| ROCContrastCoeff | L matrix from ROCCONTRAST | ROCCONTRAST | E |
| ROCContrastCov | Covariance of ROCCONTRAST rows | ROCCONTRAST | COV |
| ROCContrastEstimate | Estimates from ROCCONTRAST | ROCCONTRAST | ESTIMATE= |
| ROCContrastTest | Wald test from ROCCONTRAST | ROCCONTRAST | Default |
| ROCCov | Covariance between ROC curves | ROCCONTRAST | COV |
| RSquare | R-square | MODEL | RSQUARE |
| ScoreFitStat | Fit statistics for scored data | SCORE | FITSTAT |
| SimpleStatistics | Summary statistics for explanatory variables | PROC LOGISTIC | SIMPLE |
| StrataInfo | Event and nonevent frequencies for each stratum | STRATA | INFO |
| StrataSummary | Number of strata with specific response frequencies | STRATA | Default |
| SuffStats | Sufficient statistics | EXACT | OUTDIST= |
| TestPrint1 | L[Cov(b)]L’ and Lb-c | TEST | |
| TestPrint2 | Ginv(L[Cov(b)]L’) and Ginv(L[Cov(b)]L’)(Lb-c) |
TEST | |
| TestStmts | Linear hypotheses testing results | TEST | Default |