mitchell.d@VIDEOTRON.CA wrote: > >Hi, > >We are using proc model to do simulations. However, proc model fails to >complete the simulation with the following error: > >2692 solve lrel lng_hh oil dloil coal_ara dlcoal_ara/ dynamic >estdata=parame sdata=covamat >2692! out=Sim1 >2693 jacobi random=200 >seed=197781 ; > >ERROR: The variance for equation ERROR.dlcoal_ara is missing. The >simulation >cannot continue. >ERROR: The solution did not converge for observation 46 after 0 JACOBI >iterations using the > convergence criterion CONVERGE=1E-8 for RANDOM replication number >36. >NOTE: Simulation aborted. > >Is there a way to force the simulation to drop the problematic simulation >and keep proceeding with the remaining simulations? > >Best regards, > >Dominic.

It looks like you are asking for a Monte Carlo simulation. But that repeats the solution n times for each BY group, with different random perturbations of the equation errors if the SDATA= option is used. But you aren't giving it the equation errors. (Note the *first* error message.)

HTH, David -- David L. Cassell mathematical statistician Design Pathways 3115 NW Norwood Pl. Corvallis OR 97330

_________________________________________________________________ Find a local pizza place, movie theater, and more….then map the best route! http://maps.live.com/?icid=hmtag1&FORM=MGAC01