forum.alglib.net

ALGLIB forum
It is currently Sun Dec 22, 2024 11:13 pm

All times are UTC


Forum rules


1. This forum can be used for discussion of both ALGLIB-related and general numerical analysis questions
2. This forum is English-only - postings in other languages will be removed.



Post new topic Reply to topic  [ 5 posts ] 
Author Message
 Post subject: Linear regression
PostPosted: Mon Jul 04, 2011 2:21 pm 
Offline

Joined: Mon Jul 04, 2011 2:06 pm
Posts: 3
Hi,

I am performing some multiple linear regression with Alglib using lrbuild and lrunpack.
However, I didn't realize how to obtain the regression coefficient r2 and the standard deviation of each coefficient.

Any help?

Thank in advance

Alexandre Araripe
Federal University of Bahia
Physics Intitute
Brasil


Top
 Profile  
 
 Post subject: Re: Linear regression
PostPosted: Mon Jul 04, 2011 8:12 pm 
Offline
Site Admin

Joined: Fri May 07, 2010 7:06 am
Posts: 927
As for ALGLIB 3.4.0, such functionality is not supported. I understand that it is significant gap in the library, but these functions have lesser priority than other items. I hope that things will get better during second part of the year, when I will get more developers working on ALGLIB.


Top
 Profile  
 
 Post subject: Re: Linear regression
PostPosted: Tue Jul 05, 2011 12:36 pm 
Offline

Joined: Mon Jul 04, 2011 2:06 pm
Posts: 3
Thank you very much.
I will be connected and wainting for such changes.
By the way, congratulations for the good job you are done with AlgLib.

Alexandre Araripe
Federal University of Bahia
Physics Intitute
Brasil


Top
 Profile  
 
 Post subject: Re: Linear regression
PostPosted: Thu May 17, 2012 7:27 pm 
Offline

Joined: Thu May 17, 2012 7:22 pm
Posts: 1
Alexandre,

I was trying to solve the same issue, and I believe I have the answer to your problem. The lrreport that is returned includes a covariance matrix. The coefficient standard error is the square root of the diagonal element in that matrix.

i.e., the standard error of the jth coefficient is the [j,j] value in the covariance matrix.

hope this helps


Top
 Profile  
 
 Post subject: Re: Linear regression
PostPosted: Mon Jun 04, 2012 2:24 pm 
Offline

Joined: Mon Jul 04, 2011 2:06 pm
Posts: 3
I think this approach will be valuable.
Where can I find the math justification for this?
Thank you very much.
Araripe


Top
 Profile  
 
Display posts from previous:  Sort by  
Post new topic Reply to topic  [ 5 posts ] 

All times are UTC


Who is online

Users browsing this forum: No registered users and 36 guests


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Search for:
Jump to:  
Powered by phpBB © 2000, 2002, 2005, 2007 phpBB Group