Predictions for Bailey-Makeham
------------------------------

    ^mpredict , pparm(^parmlist^) ptime(^faillist^)^

where parmlist has one or more elements of the form:

    varname1^(alpha)^, varname2^(gamma)^, varname3^(delta)^,
    varname4^(var[alpha])^, varname5^(var[gamma])^, varname6^(var[delta])^, or
    varname7^(cov[alpha,gamma])^, varname8^(cov[alpha,delta])^,
    varname9^(cov[gamma,delta])^

and faillist has one or more elements of the form:

    varname^[^time^]^

In each case, the multiple elements are separated by spaces.
For example, in the above Karnofsky example, we might give the command

    mpredict , pparm(alpha1[alpha] gamma1[gamma] delta1[delta]) ptime(p6[180])

This would create four variables, alpha1, gamma1, delta1, and p6, which would
be merged into the current dataset.