Drexel dragonThe Math ForumDonate to the Math Forum



Search All of the Math Forum:

Views expressed in these public forums are not endorsed by Drexel University or The Math Forum.


Math Forum » Discussions » sci.math.* » sci.stat.math.independent

Topic: Pairwise test on axial distributions
Replies: 2   Last Post: Jun 16, 2009 10:21 AM

Advanced Search

Back to Topic List Back to Topic List Jump to Tree View Jump to Tree View   Messages: [ Previous | Next ]
Fijoy

Posts: 4
Registered: 6/12/09
Re: Pairwise test on axial distributions
Posted: Jun 16, 2009 10:21 AM
  Click to see the message monospaced in plain text Plain Text   Click to reply to this topic Reply

On Jun 13, 1:34 am, Ray Koopman <koop...@sfu.ca> wrote:
> On Jun 12, 8:12 am, Fijoy <tofi...@gmail.com> wrote:
>
>
>
>
>

> > Hi all,
>
> > I have two samples, s1 and s2, of axial data (set of unit vectors,
> > where sign of each vector is irrelevant). The two samples are paired,
> > i.e. each vector in s1 corresponds exactly to one vector in s2.

>
> > I want to test the null hypothesis that the means of the two samples
> > are equal. That is, I am looking for something that is similar to the
> > paired t-test on axial distributions. Does anyone know of such a test?

>
> > I do have the book "Directional Statistics" by Kanti Mardia and Peter
> > Jupp, and the book has a test for equality of means on axial
> > distributions, but this test in the book is an unpaired (indepedent)
> > version.

>
> > Thank you for your help.
>
> > Sincerely,
> > Fijoy Vadakkumpadan

>
> This is not an area that I know much about, but since no one else has
> answered, let me guess that the solution will depend on the data only
> through the squares of the inner products of corresponding s1 and s2
> vectors. Can you map that into an appropriate single-sample test?- Hide quoted text -
>
> - Show quoted text -


Thank you for the response. Off the top of my head, I suppose I could
test the squares of inner products and see how close they are to zero.
I am not sure how I can map this onto a statistical test. Anyways, I
am trying to see first if I can directly deal with the unit vectors
themselves instead of reducing them to a scalar parameter.



Point your RSS reader here for a feed of the latest messages in this topic.

[Privacy Policy] [Terms of Use]

© Drexel University 1994-2014. All Rights Reserved.
The Math Forum is a research and educational enterprise of the Drexel University School of Education.