The GLIMMIX Procedure |
To request graphics with PROC GLIMMIX, you must first enable ODS Graphics by specifying the ODS GRAPHICS ON statement. See Chapter 21, Statistical Graphics Using ODS, for more information. The GLIMMIX procedure does not produce graphs by default. You can reference every graph produced through ODS Graphics with a name. The names of the graphs that PROC GLIMMIX generates are listed in Table 38.21, along with the required statements and options.
ODS Graph Name |
Plot Description |
Option |
---|---|---|
Plot of LS-mean differences against the average LS-mean |
||
Box plots of residuals and/or observed values for model effects |
PLOTS=BOXPLOT |
|
Plot of LS-mean differences against a control level |
PLOTS=CONTROLPLOT |
|
Plot of LS-mean pairwise differences |
||
Plot of least squares means |
||
ORPlot |
Plot of odds ratios |
PLOTS=ODDSRATIO |
PearsonBoxplot |
Box plot of Pearson residuals |
PLOTS=PEARSONPANEL(UNPACK) |
PearsonByPredicted |
Pearson residuals vs. mean |
PLOTS=PEARSONPANEL(UNPACK) |
PearsonHistogram |
Histogram of Pearson residuals |
PLOTS=PEARSONPANEL(UNPACK) |
Panel of Pearson residuals |
PLOTS=PEARSONPANEL |
|
PearsonQQplot |
Q-Q plot of Pearson residuals |
PLOTS=PEARSONPANEL(UNPACK) |
ResidualBoxplot |
Box plot of (raw) residuals |
PLOTS=RESIDUALPANEL(UNPACK) |
ResidualByPredicted |
Residuals vs. mean or linear predictor |
PLOTS=RESIDUALPANEL(UNPACK) |
ResidualHistogram |
Histogram of (raw) residuals |
PLOTS=RESIDUALPANEL(UNPACK) |
Panel of (raw) residuals |
PLOTS=RESIDUALPANEL |
|
ResidualQQplot |
Q-Q plot of (raw) residuals |
PLOTS=RESIDUALPANEL(UNPACK) |
StudentBoxplot |
Box plot of studentized residuals |
PLOTS=STUDENTPANEL(UNPACK) |
StudentByPredicted |
Studentized residuals vs. mean or linear predictor |
PLOTS=STUDENTPANEL(UNPACK) |
StudentHistogram |
Histogram of studentized residuals |
PLOTS=STUDENTPANEL(UNPACK) |
Panel of studentized residuals |
PLOTS=STUDENTPANEL |
|
StudentQQplot |
Q-Q plot of studentized residuals |
PLOTS=STUDENTPANEL(UNPACK) |
Copyright © 2009 by SAS Institute Inc., Cary, NC, USA. All rights reserved.