comp.lang.idl-pvwave archive: archive » Re: Is there a good procedure for Minimum Variance Analysis?

Home » Public Forums » archive » Re: Is there a good procedure for Minimum Variance Analysis?

Show: Today's Messages :: Show Polls :: Message Navigator
E-mail to friend

Re: Is there a good procedure for Minimum Variance Analysis? [message #58380]

Tue, 29 January 2008 05:56

Wox
Messages: 184
Registered: August 2006

Senior Member

On Mon, 28 Jan 2008 17:54:58 -0800 (PST), "duxiyu@gmail.com"
<duxiyu@gmail.com> wrote:

> I want to perform the Minimum Variance Analysis on a set of magnetic
> field data.
> Is there a good procedure in IDL for this analysis?
>
> Best regards,
> Du

Don't know what it is, but in chapter 8 in this document
http://www.issibern.ch/PDF-Files/analysis_methods_1_1a.pdf
it looks like you have to make a (co)variance matrix from the X,Y and
Z components of the field data

cov(X,X) cov(X,Y) cov(X,Z)
M= cov(Y,X) cov(Y,Y) cov(Y,Z)
cov(Z,X) cov(Z,Y) cov(Z,Z)

Then get the eigenvectors with trired/triql (because M is symmetric).
The eigenvector with the smallest eigenvalue is the boundary normal.

Report message to a moderator

[Message index]

		Re: Is there a good procedure for Minimum Variance Analysis? By: Wox on Tue, 29 January 2008 05:56
		Re: Is there a good procedure for Minimum Variance Analysis? By: duxiyu@gmail.com on Thu, 31 January 2008 19:03

Previous Topic:	Aquamacs and Terminal workaround
Next Topic:	Re: CURVEFIT for multiple datasets

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Wed Oct 08 19:22:54 PDT 2025

Total time taken to generate the page: 0.00424 seconds