Bob Eberlein & The "Powell" Method

[From Fred Nickols (990508.1717 EDT)] --

Bill Powers (9905071520 MNDT) --

New subject:

I notice that Bob Eberlein (Vensim) seems to have disappeared. I have a
question that maybe someone here would care to research. In the advanced
version of Vensim, there is a very nice process for automatically varying
the parameters of a model to get the best fit between model and data. It's
referred to on the screen as the "Powell" method. I would really like to
know how this method works, because it works a whole lot better than my way
of fitting parameters. Can anyone help?

Hi, Bill.

I asked Bob about his "disappearance" a while back. I don't recall his
exact words but my recollection is that he had other work more in line with
his own goals and priorities. I'll ask him about the "Powell" method and
how it works with a not-so-subtle hint that he should include you in his
reply. BTW, Marc Abrams interacts with Eberlein from time to time so he
might beat me to it. I was supposed to go to Vensim's "Gathering" at MIT
later this month but had to cancel out owing to the unforeseen arrival of
some deliciously lucrative consulting work or I would have asked Bob face
to face. I'm sending a couple of my people and I'll duplicate my request
via them.

P.S. I LOVE the discussion of the Herrnstein posting...


Fred Nickols
Distance Consulting "Assistance at A Distance"
(609) 490-0095