The COPULA Procedure (Experimental)


The OUTCOPULA= data set consists of several rows. The first row (with _TYPE_=‘PARM’) contains the parameter estimates in the model. For a $t$ copula, the estimate is the number of degrees of freedom; for Archimedean copulas, the estimate is theta. The second row (with _TYPE_=‘STD’) contains the standard error for the parameter estimate in the model. These two rows do not appear for the normal copula.

If you use one of the elliptical copulas, $t$ or normal, the rest of the data set contains the correlation matrix estimates. The correlation matrix appears in the observations with _TYPE_=‘COR’, and the _VARIABLE_ column contains the parameter names.

If METHOD=MLE and the nonlinear optimization subsystem is used, a _STATUS_ column is created that contains a character variable that indicates whether the optimization process reached convergence or failed to converge:

  • 0 indicates that the convergence was reached

  • 1 indicates that the maximum number of iterations allowed was exceeded

  • 2 indicates a failure to improve the function value

  • 3 indicates a failure to converge for one of the following reasons:

    • The objective function or its derivatives could not be evaluated or improved.

    • Linear constraints are dependent.

    • The algorithm failed to return to feasible region.

    • The number of iterations is greater than prespecified.