| T O P I C R E V I E W |
| lenaphys |
Posted - 08/23/2015 : 10:10:03 AM
hi everyone!
Im using Hill function to fit my data.
After fiting, there are many informations about fitting in the sheet " FitNL1" such as: Residual Sum of Squares, Reduced Chi-Sqr,Adj. R-Square,.... As I know, Adj. R-Square will tell us the goodness of the fit but Im not sure about other quatities.
My question is that which quantities do I have to consider to define the goodness of the fit. thanks so much
Origin Ver. and Service Release (Select Help-->About Origin):
Operating System: |
| 1 L A T E S T R E P L I E S (Newest First) |
| SeanMao |
Posted - 08/24/2015 : 02:22:28 AM
Hi,
Apparently as you have mentioned, adjusted R^2 which is not associated with the scale of given input would be the major measure of the goodness of fit.
http://www.originlab.com/doc/Origin-Help/Interpret-Regression-Result#Goodness_of_Fit
Sometimes even if you have good R^2 value but the model used to fit the data might not be accurate, in this case residual analysis can be applied to make the judgement.
http://www.originlab.com/doc/Origin-Help/Residual-Plot-Analysis
To understand other quantities in the report sheet, you can refer the algorithm section of nonlinear fit model:
http://www.originlab.com/doc/Origin-Help/NLFit-Algorithm#How_Origin_Fits_the_Curve
Regards!
Sean
OriginLab Tech. Service
|
|
|
