The GAM Procedure |
PROC GAM Statement |
The PROC GAM statement invokes the procedure. You can specify the following options.
specifies the SAS data set to be read by PROC GAM. The default value is the most recently created data set.
reverses the sorting order of all classification variables (specified in the CLASS statement). If both the DESCENDING and ORDER= options are specified, PROC GAM orders the categories according to the ORDER= option and then reverses that order. This option has the same effect as the classification variable option DESCENDING in the CLASS statement and the response variable option DESCENDING in the MODEL statement.
specifies the sorting order for the levels of all classification variables (specified in the CLASS statement). This ordering determines which parameters in the model correspond to each level in the data. Note that the ORDER= option in the CLASS statement and the ORDER= response variable option in the MODEL statement override the ORDER= option in the PROC GAM statement.
controls the plots produced through ODS Graphics. When you specify only one plot-request, you can omit the parentheses around the plot-request. Here are some examples:
plots=all plots=components(commonaxes) plots(unpack)=components(commonaxes clm)
You must enable ODS Graphics before requesting plots as shown in the following example. With ODS Graphics enabled, the output graph by default is a panel of multiple plots of partial prediction curves of smoothing components, if PLOTS is not specified or no options are specified for PLOTS. For general information about ODS Graphics, see Chapter 21, Statistical Graphics Using ODS.
ods graphics on; proc gam data=test plots(unpack)=components(commonaxes clm); model z=spline(x) spline(y); run; ods graphics off;
The global-plot-options apply to all plots generated by the GAM procedure, unless altered by a specific-plot-option.
requests the SmoothingComponentPlot that displays a panel of smoothing component plots. The following components-options are available:
requests that the additive component plots are produced for spline and loess effects. The additive component plots combine the linear trend and the nonparametric prediction for each spline or loess effect.
includes confidence limits in the smoothing component plots. By default, 95% confidence limits are produced, but you can change the significance level by specifying the ALPHA= option in the MODEL statement. Note that producing these limits can be computationally intensive for large data sets.
specifies that smoothing component plots use a common vertical axis. This enables you to visually judge relative effect size.
specifies that the smoothing components be displayed individually.
Copyright © SAS Institute, Inc. All Rights Reserved.