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
 standard error deviates between computers

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
ria7777 Posted - 04/18/2013 : 09:16:42 AM
dear origin team!

I would like to fit several data points with error and direct weighting. However, I get different results than a friend of mine using the same data set a.nd fitting parameters. Even if I fit the data in her graph, I get the same values for intercept and slope, but significantly different values for standard errors. My friend uses origin 8.
(both graphs are attached)
How could this be? Which values are "true"?
Thanks in advance!!





Origin Ver. and Service Release (Select Help-->About Origin): OriginPro 9.0.0
Operating System: Windows 7
http://www.originlab.com/ftp/forum_and_kbase/Images/graphs incl fitting.xlsx
4   L A T E S T    R E P L I E S    (Newest First)
ria7777 Posted - 04/18/2013 : 2:24:26 PM
Hey!

Thanks a lot for your help! It's a lot clearer now.

Cheers,
Maria
matthew@originlab.com Posted - 04/18/2013 : 1:34:30 PM
Try reading through these threads:

http://www.originlab.com/forum/topic.asp?TOPIC_ID=6819

http://www.originlab.com/forum/topic.asp?TOPIC_ID=18412

Essentially, reduced Chi-Sqr divided the Chi-Sqr by degrees of Freedom. This means reduced Chi-Sqr values can be compared easily to those of models with a different number of degrees of freedom.

Matthew
OriginLab
ria7777 Posted - 04/18/2013 : 12:37:23 PM
Hi!

Thanks for answering that quickly! This tick was indeed the "problem". What exactly does it mean, when it is ticked?
In your opinion, should I use the higher or the lower values for the standard deviation?

Thanks again!

P.S. I just sent the data per Email. Thanks for the offer!
matthew@originlab.com Posted - 04/18/2013 : 09:48:44 AM
Hi,

I'm unable to open the attachments, would you mind sending them to us at tech@originlab.com

One quick thing to check would be the option to "Use Reduced Chi-Sqr" under the Advanced tab of the Non-Linear Fit dialog. By default this option is checked, un-checking it will not affect the values of the fit, but will affect the standard errors.

Matthew
OriginLab

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