The NLMIXED Procedure
-
Overview
-
Getting Started
-
Syntax
-
DetailsModeling Assumptions and NotationIntegral ApproximationsBuilt-in Log-Likelihood FunctionsHierarchical Model SpecificationOptimization AlgorithmsFinite-Difference Approximations of DerivativesHessian ScalingActive Set MethodsLine-Search MethodsRestricting the Step LengthComputational ProblemsCovariance MatrixPredictionComputational ResourcesDisplayed OutputODS Table Names
-
Examples
- References
The PREDICT statement enables you to construct predictions of an expression across all of the observations in the input data set. Any valid SAS programming expression involving the input data set variables, parameters, and random effects is valid. Predicted values are computed using the parameter estimates and empirical Bayes estimates of the random effects. Standard errors of prediction are computed using the delta method (Billingsley, 1986; Cox, 1998). Results are placed in an output data set that you specify with the OUT= option. Besides all variables from the input data set, the OUT= data set contains the following variables: Pred, StdErrPred, DF, tValue, Probt, Alpha, Lower, Upper. You can also add other computed quantities to this data set with the ID statement.
The following options are available in the PREDICT statement:
-
ALPHA=
-
specifies the alpha level to be used in computing t statistics and intervals. The default value corresponds to the ALPHA= option in the PROC NLMIXED statement.
- DER
-
requests that derivatives of the predicted expression with respect to all parameters be included in the OUT= data set. The variable names for the derivatives are the same as the parameter names with the prefix "Der_" appended. All of the derivatives are evaluated at the final estimates of the parameters and the empirical Bayes estimates of the random effects.
- DF=d
-
specifies the degrees of freedom to be used in computing t statistics and intervals in the OUT= data set. The default value corresponds to the DF= option in the PROC NLMIXED statement.