Subsections:

The following sections describe the output PROC HPMIXED produces by default. This output is organized into various tables, and they are discussed in order of appearance.

The “Model Information” table describes the model, some of the variables it involves, and the method used in fitting it. It also lists the method for computing the degrees of freedom.

The name of the “Model Information” table is ModelInfo.

The “Class Level Information” table lists the first 20 levels of every variable specified in the CLASS statement. You should check this information to make sure the data are correct. You can adjust the order of the CLASS variable levels with the ORDER= option in the PROC HPMIXED statement. The name of the “Class Level Information” table is ClassLevels.

The “Dimensions” table lists the sizes of relevant matrices. This table can be useful in determining CPU time and memory requirements. The name of the “Dimensions” table is “Dimensions.”

The “Number of Observations” table shows the number of observations read from the data set and the number of observations used in fitting the model.

The “Descriptive Statistics” table lists simple statistics such as means and standard deviations for the dependent variable, for each covariate in the MODEL statement, and for the weight variable in the WEIGHT statement.

The “Iteration History” table describes the optimization of the residual log likelihood. The function to be minimized (the *objective function*) is .

The name of the “Iteration History” table is IterHistory.

The “Covariance Parameter Estimates” table contains the estimates of the parameters in and . Their values are labeled in the “Cov Parm” table along with Subject and Group information if applicable. The estimates are displayed in the Estimate column.

The name of the “Covariance Parameter Estimates” table is CovParms.

The “Convergence Status” table contains a status message that describes the reason the optimization terminated. The message is also written to the
log. The name of the “Convergence Status” table is ConvergenceStatus. You can query the nonprinting numeric variable `Status`

to check for a successful optimization. This is useful in batch processing, or when processing BY groups, such as in simulations.
Successful optimizations are indicated by the value 0 for the `Status`

variable.

The “Fit Statistics” table provides some statistics about the estimated mixed model.

In addition, the “Fit Statistics” table lists three information criteria: AIC, AICC, and BIC, all in smaller-is-better form. Expressions for these criteria are described under the IC= option.

The name of the “Model Fitting Information” table is FitStatistics.