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
 error message in nonliner fitting(nlsf)		  New Topic  Reply to Topic
 Printer Friendly
Author Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic

weijian

USA
3 Posts
Posted - 05/17/2001 :  12:52:59 PM  Show Profile  Edit Topic  Reply with Quote  View user's IP address  Delete Topic
The message is:
error 28036, try setting parameter "P5" as fixed.

I am using user defined function(chebychev):
y = P1+P2*x+P3*cos(2*acos(x))+P4*cos(3*acos(x))
P5*cos(4*acos(x))+P6*cos(5*acos(x))+P7*cos(6*acos(x))
+P8*cos(7*acos(x))

This is not too long, right?

Laurie

USA
404 Posts
Posted - 05/18/2001 :  3:16:02 PM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
It's length should not be a problem. I do notice that you have a missing '+' symbol before the P5. Is this just a typo in your post?

OriginLab Technical Support
Go to Top of Page

weijian

USA
3 Posts
Posted - 07/16/2001 :  12:44:12 PM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Sorry for late reply, I juct come back.

It was a typo. In fact when I try it with 4 parameters, it is ok, but when use 5 parameters, can't even simulate under the Action menu. :(

Following is the data I want to fit:

Y X

1.4836 1
1.9958 0.55522
2.3983 0.31965
2.8098 0.13895
3.2349 -0.00634
3.6012 -0.10824
4.0128 -0.20351
4.2212 -0.24562
4.6211 -0.31709
5.4058 -0.43128
6.2197 -0.52348
7.0661 -0.59951
8.0505 -0.67046
9.0859 -0.73106
10.0464 -0.77777
11.0254 -0.81825
13.1481 -0.88856
14.238 -0.91788
16.1212 -0.96083
18.2201 -1
Go to Top of Page

Laurie

USA
404 Posts
Posted - 07/19/2001 :  09:22:32 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
This type of question is best to email or call us directly with. I will need the initial guesses for the parameters. Also I notice that your data is designated as YX...you might want to move the Y column ahead of the X column (select Column:Move to First)...just make sure that you've assigned the correct XY variables when fitting.

Feel free to drop me an email at tech@originlab.com.

OriginLab Technical Support
Go to Top of Page

weijian

USA
3 Posts
Posted - 07/29/2001 :  6:19:25 PM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi, Laurie:

I got the nice result finally:

Data: Data1_Temp
Model: weijian2

Chi^2 = 1.251E-8
R^2 = 1

a0 2.92057 \(177)0.00129
a1 -1.84318 \(177)0.00214
a2 0.48033 \(177)0.00091
a3 -0.12054 \(177)0.0004
a4 0.03687 \(177)0.00127
a5 0.00035 \(177)0.00139
a6 0.00693 \(177)0.00092
a7 0.00227 \(177)0.00037

here \(177) means plus or minus.

The trick is I add another column, say "acos", to calculate the value of acos(x) first.
Then just use cos(*)... Then it is all ok.
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