| T O P I C R E V I E W |
| jospector |
Posted - 02/09/2009 : 3:42:05 PM
Origin Ver. and Service Release (Select Help-->About Origin): 8.0 SR4
Operating System: XP
Hi all,
I've got two sets of data, each of which should fit to a gaussian. I'd like to fit them together to a surface as that will save time. The problem is that they need to be fit to a rotated gaussian. My fit function is:
z = z0 + A*exp( -0.5*( ( (x*cos(theta)-y*sin(theta))-(xc*cos(theta)-yc*sin(theta)) )/w1)^2 -0.5*( ( (x*sin(theta)+y*cos(theta))-(xc*sin(theta)+yc*cos(theta)) )/w2)^2 ) ;
but it seems to never converge..is there a better way to do this?
My data represent the positions of a particel over time. The purpose of the rotation is to coincide the axis with the "long" direction of the trajectory...
thanks,
-js- |
| 2 L A T E S T R E P L I E S (Newest First) |
| jospector |
Posted - 02/10/2009 : 9:20:29 PM
submitted it today.
The file attachments wouldn't' let me use a .fdf so I made it a .txt file instead.. |
| Deanna |
Posted - 02/10/2009 : 01:36:50 AM
Would you please send your data and the definition file (.fdf file) of the fitting function to us? With your data and function, we can do some test to see what happens.
Please read the following instructions on how to send files to OriginLab:
http://www.originlab.com/index.aspx?s=1&lm=123&pid=752
Deanna
OriginLab Technical Services |
