Shared Concepts and Topics

(View the complete code for this example.)

Most procedures that iterate create a table named ConvergenceStatus. The table contains a numeric column named Status and a character column named Reason. When iterations complete successfully, the status is 0. Values greater than 0 indicate something other than a successful convergence. Larger values indicate more severe problems. Different procedures produce different values for different reasons. Consult the Reason column and the SAS log for more information about nonzero values. Batch users can create an output data set from the ConvergenceStatus table and consult it to determine how to proceed with the analysis.

Sample values include the following:

The following steps illustrate how to display the convergence status:

data heights;
   input Family Gender $ Height @@;
   datalines;
1 F 67   1 F 66   1 F 64   1 M 71   1 M 72   2 F 63
2 F 63   2 F 67   2 M 69   2 M 68   2 M 70   3 F 63
3 M 64   4 F 67   4 F 66   4 M 67   4 M 67   4 M 69
;

proc mixed data=heights method=ml;
   ods output convergencestatus=cs;
   class Family Gender;
   model Height = Gender Family Family*Gender;
   repeated / type=un subject=family r;
run;

proc print data=cs;
   id status;
run;

The iteration history and convergence status table are displayed in Output 19.14. The convergence status data set is displayed in Output 19.15. The nonzero status indicates that there is a problem with the results.

The results converge in the following example:

proc mixed data=heights method=ml;
   ods output convergencestatus=cs;
   class Family Gender;
   model Height = Gender Family Family*Gender;
   repeated / type=ar(1) subject=family r;
run;

proc print data=cs;
   id status;
run;

The iteration history, convergence status table, and convergence status data set are displayed in Output 19.16.