This post focus on the ODS Output for regression, including ANOVA, least square means, parameter estimates etc.
Each output from a SAS procedure has an associated name and label. Each name is part of a name path, and each label is part of a label path. In order to select, exclude, or modify an output table, you must first know its name. Each level in the name path corresponds to a part of the procedure’s hierarchy of output that you can view in the Results window.
ods output parameterestimates = outputtable1 fitstatistics = outputtable2 overallanova = outputtable3 lsmeans = outputtable4 nobs = outputtable5 means = outputtable6;
| ODS table name | Statement / Option | Key Stats |
|---|---|---|
| ParameterEstimates | Model / Solution | Estimated linear model coefficients, t Value, Probability T, standard error |
| FitStatistics | Default | r-square, Coeff Var, Root MSE, dependent mean |
| OverallAnova | Default | DF, sum of squares, mean square, F value, Probability F |
| LsMeans | LsMeans | Least squares means are requested for each effect listed in the LSMEANS statement. LSMEANS can perform on classification variables and multiple comparison on interactions. LSMEANS are predicted population margins; that is, they estimate the marginal means over a balanced population. |
| Nobs | Default | Number of Observations |
| Means | Means | When variables in the Means statement is the same as in the Model statement, Means statement will provide the count of observations for each model effect or combination of effects. |
BI Practice 