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
 Uncertanity analysis using cut-off or Threshold va		  New Topic  Reply to Topic
 Printer Friendly
Author Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic

kmgraju

Malaysia
18 Posts
Posted - 07/23/2015 :  02:46:57 AM  Show Profile  Edit Topic  Reply with Quote  View user's IP address  Delete Topic
Dear members,
I have an experimentally measured data points(y) for the variable x. These data points are random data and collected from more than 100 samples. I have plotted these points in a graph (x,y) and find the correlation between them. It was non-linear second order polynomial.
I have a cut-off value in the experimentally measured data points. I want to do uncertainty analysis or in other words I want to find out the uncertainty range in the variable x using the cut-off value.

What is the best statistical method could be adopted to find out the uncertainty range

Thank you for your time

Thank you

kmgraju

SeanMao

China
288 Posts
Posted - 07/23/2015 :  03:58:03 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi,

I am not so sure what you are looking for exactly, but I am guessing you are looking for the Confidence Band (uncertainty range) with self-defined Confidence Level (cutoff) for a second polynomial fitting.

We have a figure in Polynomial Fit section which highlight confidence interval by pink filling in the graph:

http://originlab.com/index.aspx?go=Products/Origin/DataAnalysis/CurveFitting/LinearAndPolynomialFitting#5

If this is what you want, you can make use of our Polynomial Fit tool and set Confidence Level for Parameters(%) in the dialog under Quantities to Compute: Fit Parameters node.

Regards!

Sean

OriginLab Tech. Service
Edited by - SeanMao on 07/23/2015 03:59:14 AM
Go to Top of Page

kmgraju

Malaysia
18 Posts
Posted - 07/23/2015 :  05:04:46 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Thank you for your reply. It is similar like what I expected.
I have few questions
How bootstrapping method is useful to find the uncertainty range in the variable along the x-axis with the cutoff value at the y-axis ?
Is it same as you mentioned earlier?

Thank you

kmgraju
Edited by - kmgraju on 07/23/2015 05:11:35 AM
Go to Top of Page

SeanMao

China
288 Posts
Posted - 07/23/2015 :  9:19:07 PM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi,

The algorithm in finding the confidence interval in polynomial regression is in page below:

http://www.originlab.com/doc/Origin-Help/PR-Algorithm

Regards!

Sean
Go to Top of Page

kmgraju

Malaysia
18 Posts
Posted - 07/23/2015 :  11:11:48 PM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Thank you for your reply.

from my experimental samples for the same x value I am getting a different y value. But I have a set point or cutoff point in my Y variable. I would like to find out the range in the variable x where the uncertainty takes place by using the cutoff point.

I would like to know, can I use the method which you have suggested is applicable?

and what is bootstrapping? is this method used to find the confidence interval?



Thank you
Go to Top of Page

SeanMao

China
288 Posts
Posted - 07/27/2015 :  01:49:41 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi,

Currently we do not support computing confidence intervals using bootstrapping regression.

Regards!

Sean
Go to Top of Page

kmgraju

Malaysia
18 Posts
Posted - 10/31/2015 :  03:17:59 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi,
Is there any update about Bootstrap regression

Thank you

Govind
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