The LOGISTIC Procedure

The MARGINS statement computes and compares predictive margins of fixed effects. The predictive margin for a specific level (group) of a fixed effect represents the average predicted response if all the observations in the data set were in that group (Lane and Nelder 1982; Chang, Gelman, and Pagano 1982). You can compute predictive margins for any effect in the MODEL statement that involves only classification variables.

Table 7 summarizes the options available in the MARGINS statement.

Table 7: MARGINS Statement Options

Option	Description
Construction and Computation of Predictive Margins
AT	Modifies the covariate value in computing predictive margins
DIFF	Computes differences of predictive margins
SLICEBY=	Partitions tests of interaction effects
SLICEDIFF	Computes differences of sliced predictive margins and determines the types of differences
USEWEIGHT	Specifies whether to use WEIGHT variables to compute predictive margins
Degrees of Freedom and p-Values
ADJUST=	Specifies the method of multiple comparison adjustment of predictive margin differences
ALPHA=	Specifies the confidence level ()
STEPDOWN	Adjusts multiple comparison p-values further in a step-down fashion
Statistical Output
CL	Constructs confidence limits for predictive margins and/or predictive margin differences

For more information about the syntax of the MARGINS statement, see the section MARGINS Statement in Chapter 20, Shared Concepts and Topics.

Note: By default, chi-square and z tests are produced, and weights are not used in the computations. If your model has classification variables, then the MARGINS statement is allowed only if you also specify the PARAM=GLM option.