jmarotta wrote:
> Hi everyone,
> This is probably a bit of a stupid question. I'm trying to fit using
> the Levenberg-Marquardt algorithm contained in Labview. As you are
> all no doubt aware, you need an initial guess to start the algorithm.
> Does anyone have a good way of automating the initial guess, so that I
> don't have to re-enter it by hand every time? I'm testing using
> random data.
> Thanks,
> Joe
Joe,
You don't say what function you are fitting. I have a program on my
web site that does just what you are asking for for a Gaussian peak fit.
It makes certain assumptions (such as - there is only one peak in the
data, and its amplitude is positive). It scans the data to make decent
first guesses at the fit coefficients and is thereaft
er usually
successful at fitting the data without diverging.
Let me know if you can't find the Gaussian Peak Fit routine on my
web site.
Regards,
Dave
-------------------------------------------------------------
David Thomson 303-499-1973 (voice and fax)
Original Code Consulting dthomson@originalcode.com
www.originalcode.com
National Instruments Alliance Program Member
Certified LabVIEW Developer
Certified Instrument Driver Developer
-------------------------------------------------------------
Research Scientist 303-497-3470 (voice)
NOAA Aeronomy Laboratory 303-497-5373 (fax)
Boulder, Colorado dthomson@al.noaa.gov
-------------------------------------------------------------
There are 10 kinds of people: those who understand binary,
and those who don't.
