PROC NLMIXED now enables you to specify more than one RANDOM statement in order to fit hierarchical nonlinear mixed models.
The OUTR= option in the PROC NLMIXED statement requests an output data set that contains all the random-effects variable estimates from all RANDOM statements.
The default degrees of freedom for the fixed parameters is calculated for random-effects models as the total number of subjects minus the number of random-effects variables that are specified in a RANDOM statement. If this calculation produces a nonpositive number, the default degrees of freedom is replaced by the total number of observations.