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
 All Forums
 Origin Forum
 Origin Forum
 Non linear curve fitting -

Note: You must be registered in order to post a reply.
To register, click here. Registration is FREE!

Screensize:
UserName:
Password:
Anti-Spam Code:
Format Mode:
Format: BoldItalicizedUnderlineStrikethrough Align LeftCenteredAlign Right Horizontal Rule Insert HyperlinkUpload FileInsert Image Insert CodeInsert QuoteInsert List
   
Message:

* HTML is OFF
* Forum Code is ON
Smilies
Smile [:)] Big Smile [:D] Cool [8D] Blush [:I]
Tongue [:P] Evil [):] Wink [;)] Clown [:o)]
Black Eye [B)] Eight Ball [8] Frown [:(] Shy [8)]
Shocked [:0] Angry [:(!] Dead [xx(] Sleepy [|)]
Kisses [:X] Approve [^] Disapprove [V] Question [?]

 
Check here to subscribe to this topic.
   

T O P I C    R E V I E W
Bobby64 Posted - 02/08/2012 : 2:26:49 PM
Origin Ver. and Service Release (Select Help-->About Origin): 6 +8.5
Operating System: Windows

Hi,

I have a question related to the non linear fitting procedure with Origin. I guess it must be basic for all mathematicians, but I have to admit that my knowledge in this field is a bit limited...

Here is my question:
I run some non linear fittings of experimental data points using a user defined function. When the fitting iterations are done, and the X-square is reduced, I have a final result showing the values of all the fitted parameters with the associated standard errors.

So, my question is to know whether this standard error calculated by Origin corresponds to 1-sigma or 2-sigma of standard deviation ?

I had a look to the help, but, to be honnest, I didn't find anything so specific... For those who have the answer, could you give where it is written is the help manual?

Many thanks in advance for your help,


Bobby64
2   L A T E S T    R E P L I E S    (Newest First)
Bobby64 Posted - 02/10/2012 : 03:32:45 AM
Hi Hideo Fujii,

many thanks for your answer, it helps me a lot.

Cheers

Bobby64
Hideo Fujii Posted - 02/08/2012 : 5:00:15 PM
Hi Bobby64,

I'm not a mathematician nor a statistician, but my basic understanding is that Standard Error(SE) (of Meam, SEM) is, for calculation of the confident interval, a reduced, or normalized value of Standard Deviation(SD) - SD divided by a square root of sample size. In your term, if I dare to say, SE is 1-sigman reduced SD, thus +/-1.96*SE is the 95% range (1.96 for large N, otherwise t95 value).
Origin's NLFit has also an option to output the confident intervals, LCL and UCL of a given confidence level.

You can find the details of SE of estimated parameters in the Origin help at:
UserGuide> Regression and Curve Fitting> Nonlinear Curve Fitting> The Fit Results> Parameter Standard Errors
(Please don't ask me the meaning of the formula, or go... :"-) )

Hope the above is a good start for you.

--Hideo Fujii
OriginLab

The Origin Forum © 2020 Originlab Corporation Go To Top Of Page
Snitz Forums 2000