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
 ExpDec varying start value
 New Topic  Reply to Topic
 Printer Friendly
Author Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic

chrisUser

Germany
2 Posts

Posted - 04/19/2017 :  08:33:38 AM  Show Profile  Edit Topic  Reply with Quote  View user's IP address  Delete Topic
Origin Ver. and Service Release: OriginPro9.1.0G (64-bit) Sr3
Operating System: Windows 7

Hey guys,

following situation:

I have a data set which is exponential, so I can fit an exponential decay function, in detail it's the ExpDec1 function that fit's my data best. I now need to define an x range of values in which my fit takes place. Furthermore I need to define the amount of x values that are included in the fit and the function now has to find the best fit (including start value) by itself in the x range that was initially given by me. So I think the x value needs to be a parameter, too, but I don't know how to handle this. Is this possible? I'm not an expert in this programm and in programming itself.

Best regards
Chris

On the picture you can see my situation decribed. The marks symbolize the range where the fit should take place.


Edited by - chrisUser on 04/19/2017 08:38:28 AM

arstern

USA
237 Posts

Posted - 04/19/2017 :  11:05:37 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi Chris,

1) You can specify the x range of values for your fitted curve by selecting the Data Selection under the Settings tab. Under Rows you can select your range by x or by row number.



2) You can specify the amount of x values by selecting Fitted Curve under the Settings tab. Input the number of points under X Data Type that you want to plot.



Thanks,

Aviel
OriginLab
Go to Top of Page

YimingChen

1609 Posts

Posted - 04/19/2017 :  11:57:36 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi Chris,

Basically taking the starting x value(x0) as fitting parameter won't work here. Because the fitting algorithm gets best fitting by minimizing the residual sum of square: sum(y_fit - y)^2, which always decreases as the number of data points decreases. You will probably end up with a x0 value so that only few data points are included in the range for fitting. Thanks.

Yiming
Go to Top of Page

chrisUser

Germany
2 Posts

Posted - 04/20/2017 :  04:54:10 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hey you both,

many thanks for your quick answer!

@Aviel, this is what I already know, but this doen't eliminate the problem of dynamic range for the fit with a varying start value.

@Yiming, not glad to here.. Isn't there a possibility to solve the problem?
Go to Top of Page

Sam Fang

293 Posts

Posted - 04/21/2017 :  04:51:36 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi Chris,

Parameter for x start value can't change range of input data in the fitting. You can use loop to fit data by increasing the x start value each time, and find the x start value whose Reduced ChiSqr is the smallest or R-Square value is close to 1.

We once help a customer find the range of linear section.

Sam
OriginLab Technical Services
Go to Top of Page

chrisUser

Germany
2 Posts

Posted - 04/27/2017 :  05:51:44 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Thank you for your help!
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