For Programmers: Free Programming Magazines  


Home > Archive > Matlab > December 2005 > fitting simultaneously multiple data set









You are viewing an archived Text-only version of the thread. To view this thread in it's original format and/or if you want to reply to this thread please [click here]

 

Author fitting simultaneously multiple data set
peter normile

2005-12-13, 8:19 am

Hi,

I have two data sets which I want to fit to the same functional form,
with certain parameters the same for both fits, and others differing.
e.g.,

data set 1, y1(x1)
data set 2, y2(x2)

fit to y1 is f1(x1,p1), p1 is parameter vector
fit to y2 is f2(x2,p2), p2 is parameter vector

p1 = [p1(1) p1(2) p1(3) p1(4) p1(5)]
p2 = [p2(1) p2(2) p2(3) p2(4) p2(5)]

and p2(2) = p1(2), p2(3) = p1(3)

Total of number of parameters to fit = 8

Can anyone point in the right direction?

peter
John D'Errico

2005-12-13, 7:11 pm

In article <ef1eb3a.-1@webx.raydaftYaTP>,
"peter normile" <peter_normile@yahoo.co.uk> wrote:

> I have two data sets which I want to fit to the same functional form,
> with certain parameters the same for both fits, and others differing.
> e.g.,
>
> data set 1, y1(x1)
> data set 2, y2(x2)
>
> fit to y1 is f1(x1,p1), p1 is parameter vector
> fit to y2 is f2(x2,p2), p2 is parameter vector
>
> p1 = [p1(1) p1(2) p1(3) p1(4) p1(5)]
> p2 = [p2(1) p2(2) p2(3) p2(4) p2(5)]
>
> and p2(2) = p1(2), p2(3) = p1(3)
>
> Total of number of parameters to fit = 8
>
> Can anyone point in the right direction?



No problem. Merge the two into one larger least
squares problem, with some parameters used for
both problems and some parameters only needed for
one of the segments.

HTH,
John D'Errico


--
The best material model of a cat is another, or preferably the same, cat.
A. Rosenblueth, Philosophy of Science, 1945

Those who can't laugh at themselves leave the job to others.
Anonymous
peter normile

2005-12-18, 7:58 am

John D'Errico wrote:
>
>
> In article <ef1eb3a.-1@webx.raydaftYaTP>,
> "peter normile" <peter_normile@yahoo.co.uk> wrote:
>
> form,
> differing.
>
>
> No problem. Merge the two into one larger least
> squares problem, with some parameters used for
> both problems and some parameters only needed for
> one of the segments.
>
> HTH,
> John D'Errico
>
>
> --
> The best material model of a cat is another, or preferably the
> same, cat.
> A. Rosenblueth, Philosophy of Science, 1945
>
> Those who can't laugh at themselves leave the job to others.
> Anonymous
>

Many thanks, this worked!
peter
Sponsored Links







Also available: Server administration forum archive | Web Design forum archive | Software forum archive | Hardware reviews archive

Copyright 2008 codecomments.com