www.phidot.org

Hello: I tried to run a model.average on a set of Robust Design models, but the models are dropped because "one or more beta variances are not positive" I fear this means I have more global problems and this is just a symptom, but on the off chance that it is not, is there any way to force the average?

Mike.

See ?model.average.marklist

set argument drop=FALSE

D'Oh! Thanks Jeff. Should have guessed it would be that easy, especially when I could not find it in a search here.