The Origin Forum
File Exchange
Try Origin for Free
The Origin Forum
Home | Profile | Register | Active Topics | Members | Search | FAQ | Send File to Tech support
Username:
Password:
Save Password
Forgot your Password? | Admin Options

 All Forums
 Origin Forum
 Origin Forum
 Criteria for choosing the best fit
 New Topic  Reply to Topic
 Printer Friendly
Author Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic

a_user

USA
0 Posts

Posted - 08/12/1998 :  5:10:00 PM  Show Profile  Edit Topic  Reply with Quote  View user's IP address  Delete Topic
Hi everybody,
Currently it is not possible to use the fitting functions that Origin provides
if the user can not predetermine the type of the fitting equation. This may
seem trivial but it not can not be decided, based on the chi square only, which
one of the one, two, three etc. exponential equations represents the best fit.
We are currently trying to find solution to this problem by using Labtalk
scirpts and Basic programming. However, it would be very nice if someone can
give us some hints concerning the statisitcal analyses to be used?

a_user

USA
0 Posts

Posted - 08/12/1998 :  5:11:00 PM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
The F test to Compare Fitting Equations

Unfortunately, Origin cannot predetermine which fitting function to use. The best way to compare fits with the same fitting equation is to compare the chi square value. However, this is not the best comparison for fits with different fitting equations. The standard way to compare these is the F test. F is defined as the following: F = {(SS1-SS2) / (DF1-DF2)} / {SS2/DF2} where SS1 and SS2 are the Sum of the Squares of each fit and DF1 and DF2 are the Degrees of Freedom for each fit. An F value close to 1.0 will indicate that first fit is correct.

Although at this time Origin does not calculate the F value for consecutive fits, you can get all needed values to calculate F. After performing a fit the Sum of Squares is stored in NLSF.SSR and the Degrees of Freedom is stored in NLSF.DOF. You can access these values through the script window by typing the following,

NLSF.SSR= (return)

You can also create your own LabTalk scripts to store these values and then calculate the F values.

Go to Top of Page
  Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic
 New Topic  Reply to Topic
 Printer Friendly
Jump To:
The Origin Forum © 2020 Originlab Corporation Go To Top Of Page
Snitz Forums 2000