T O P I C R E V I E W |
elvis_xia |
Posted - 01/02/2006 : 08:30:10 AM Origin Version (Select Help-->About Origin): Operating System: I use the same fitting function to fit a group of data by diffenent fitting method. One result is done by Origin and the other is not. Now I want to compare the goodness of the two results. I think the parameter chi^2/DOF can finish the work. But I have two question: 1. is the fitting result the same one by Origin? one way is: analysis- non-linear curve fitting the other is: tools - polynomial fit 2.the definetion of chi^2/dof is ? sum(data point-fuction point)^2/dof, where dof=data point-number of parameter? |
3 L A T E S T R E P L I E S (Newest First) |
minimax |
Posted - 01/05/2006 : 06:50:52 AM Hi Elvis,
Origin 7.5 does not support weights in both coordinates. And we will add weights in both coordinates into linear fit in Origin version 8.
quote:
Thank you for your reply. But I have another two queations. The first is, is it true that Origin can only fit data with error in one coordinate? I think it seems that during my investigation. The other is how to give chi^2 with weights in both coordinates? Furthermore, I found that the fitting curve derived from the following two is the same.(I use 7.5 edition) (1) tools- polynomial fit- setting(choose error as weight and use reduced chi^2) (2)analysis -NLSF- advanced fitting tool - use control to set weight.
Edited by - elvis_xia on 01/03/2006 07:22:23 AM
Edited by - elvis_xia on 01/03/2006 07:25:36 AM
Edited by - elvis_xia on 01/03/2006 07:26:34 AM
Max OriginLab GZoffice |
elvis_xia |
Posted - 01/02/2006 : 10:38:20 PM Thank you for your reply. But I have another two queations. The first is, is it true that Origin can only fit data with error in one coordinate? I think it seems that during my investigation. The other is how to give chi^2 with weights in both coordinates? Furthermore, I found that the fitting curve derived from the following two is the same.(I use 7.5 edition) (1) tools- polynomial fit- setting(choose error as weight and use reduced chi^2) (2)analysis -NLSF- advanced fitting tool - use control to set weight.
Edited by - elvis_xia on 01/03/2006 07:22:23 AM
Edited by - elvis_xia on 01/03/2006 07:25:36 AM
Edited by - elvis_xia on 01/03/2006 07:26:34 AM |
Mike Buess |
Posted - 01/02/2006 : 09:22:38 AM 1. NLSF's Parabola fitting function with no additional constraints or weighting gives the same result as Tools > Polynomial Fit.
2. Correct for an unweighted fit. Otherwise multiply each term in the sum by the appropriate weight. Your expression for dof is correct.
Mike Buess Origin WebRing Member |