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
 report Fitting function malinterpretation

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
ChrisUVA Posted - 04/09/2005 : 2:44:26 PM
Origin Version (Select Help-->About Origin): 7.0383
Operating System: WinXP

Hello there,

this is more a report about the very unpleasent discovery, that the interpretation of log(x) is different for the Advanced Fitting tool and a standard function window.

When fitting a certain group of data, I defined the following function (I now copy and paste directly from the entry fields):

y=P * 1/( 1+ w * ( log(x/c0) )^2 )
which gave me the following answers, and a nice matching curve.
P 0.25069 \(177)6.2211E-18
w 0.49039 \(177)4.1493E-17
c0 0.838 \(177)2.9356E-17

However, when I called a new Function window, and typed this very formula the curve did neither match the data nor the generated fitting funtion. To get it matching, I had to modify it to:

0.25069 * 1 / ( 1 + 2.6* log(x/0.838)^2 )

I tried the following:

0.25069 * 1/(1+ 0.49039*ln(x/0.838)^2 ) and indeed, that gave a perfect match.

To be really sure, I used the last function to generate a group of points, and used again the advanced fitting tool with the first function on it, and I got again the same result.

My conclusion is, that the Advanced fitting tool consideres log(x) as the natural logarithm, while the Function window considers it as the base 10 logarithm.
I could not see, if this problem is known or not. Neither did I find a remark in the help function.
Please comment.

regards,
ChB

3   L A T E S T    R E P L I E S    (Newest First)
Mike Buess Posted - 04/09/2005 : 4:04:27 PM
It's on your Help menu...

Help > Programming > LabTalk Language Reference

BTW, the quote I gave above was from the Origin 7.0 SR4 (v7.0552) programming guide. I don't know which service release v7.0383 is but you might consider updating to SR4.

Mike Buess
Origin WebRing Member
ChrisUVA Posted - 04/09/2005 : 3:47:56 PM

indeed, origin C was checked true.

Where can I find the LabTalk Programming guide?
Note, that no documentation in physical form (i.e. books) is handed to the employees here.

thanks for the confirmation,
regards,
ChB
Mike Buess Posted - 04/09/2005 : 3:22:42 PM
From the LabTalk programming guide...
quote:
log(x)
The log(x) function returns the base 10 logarithm value of x.

Note: The LabTalk log function is based on 10 while the Origin C log function is based on e. The Origin C base 10 logarithmic function is log10.
The Advanced Fitting tool has an option for fitting with Origin C and you undoubtedly have that option checked.

Mike Buess
Origin WebRing Member

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