comp.lang.idl-pvwave archive: archive

Home » Public Forums » archive » Re: 2-d fitting

Show: Today's Messages :: Show Polls :: Message Navigator
E-mail to friend

Re: 2-d fitting [message #63532 is a reply to message #63522]

Wed, 12 November 2008 05:29

xqinshan
Messages: 21
Registered: November 2008

Junior Member

On 11月12日, 下午3时02分, Craig Markwardt <cbmarkwa...@gmail.com> wrote:
> On Nov 12, 12:25 am, xqinshan <xqins...@tom.com> wrote:
>
>> Hi,
>> I have a set of data zi at indepent vaiables (xi,yi). I want to get
>> coefficients of a fiting function such as f(x,y)=a*f1(x,y)+b*f2(x,y)
>> +c*f3(x,y)+..., f1(x,y),f2(x,y)... are given by myself. If f1(x,y),f2
>> (x,y)... are polunomials, we can use sfit or mpfitfun to do it. Are
>> there any routins to do it?
>
> Yes, but MPFITFUN is not limited to polynomials, it can be any
> function you wish, including multiple variables.
>
> http://www.physics.wisc.edu/~craigm/idl/fitqa.html#multivar
>
> If the user function is a linear combination of known functions, then
> SVDFIT can also be used.
>
> Craig

I have tried cof=svdfit([x,y],z,a=a), it returns "SVDFIT: The input X
must be a vector"!

Report message to a moderator

[Message index]

		Re: 2-d fitting By: R.G. Stockwell on Wed, 12 November 2008 10:00
		Re: 2-d fitting By: xqinshan on Wed, 12 November 2008 05:29
		Re: 2-d fitting By: Craig Markwardt on Tue, 11 November 2008 23:02
		Re: 2-d fitting By: xqinshan on Wed, 12 November 2008 17:39

Previous Topic:	latitude, longitude and a data point
Next Topic:	How to control character size freely?

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Fri Oct 10 13:21:59 PDT 2025

Total time taken to generate the page: 1.04082 seconds