testing variance covariance matrix equality

[Safa Gurcan]

In discriminant analysing, which test is used to determine whether sample
groups variance covariances are equal or not?
thanks.

Safa

[Albert-Jan Roskam]

It *may* be Mauchly's test of sphericity of
covariance. If it is violated, the matrices are
significantly different.

Albert-Jan

--- Safa Gurcan <[hidden email]> wrote:

> In discriminant analysing, which test is used to
> determine whether sample
> groups variance covariances are equal or not?
> thanks.
>
> Safa
>


Cheers!
Albert-Jan

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Did you know that 87.166253% of all statistics claim a precision of results that is not justified by the method employed? [HELMUT RICHTER]
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~



____________________________________________________________________________________
Looking for a deal? Find great prices on flights and hotels with Yahoo! FareChase.
http://farechase.yahoo.com/

[Anthony Babinec]

Box's M test tests for equality of covariance matrices
across groups. However, it is sensitive to departures
from normality.

To obtain it, when using Discriminant, press the Statistics
button and check the box for Box's M.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Safa Gurcan
Sent: Tuesday, August 14, 2007 7:57 AM
To: [hidden email]
Subject: testing variance covariance matrix equality

In discriminant analysing, which test is used to determine whether sample
groups variance covariances are equal or not?
thanks.

Safa

[Swank, Paul R]

Mauchley's test of sphericity is a test of the form of the variance
covariance matrix not equality. Anthony is correct that Box's M test wil
test for equality. There is also a Box test for the form of the matrix
but that is not of concern here. As Anthony said, Box's test is very
sensitive to lack of normality. Tests of equality of variance covariance
matrices can also be done with Structural Equation Modeling programs.
These procedures also have assumptions of multivariate normality but may
be less sensitive than Box's test, particularly when skewed data is
present.


Paul R. Swank, Ph.D. Professor
Director of Reseach
Children's Learning Institute
University of Texas Health Science Center-Houston


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Albert-jan Roskam
Sent: Tuesday, August 14, 2007 8:12 AM
To: [hidden email]
Subject: Re: testing variance covariance matrix equality

It *may* be Mauchly's test of sphericity of covariance. If it is
violated, the matrices are significantly different.

Albert-Jan

--- Safa Gurcan <[hidden email]> wrote:

> In discriminant analysing, which test is used to determine whether
> sample groups variance covariances are equal or not?
> thanks.
>
> Safa
>


Cheers!
Albert-Jan

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Did you know that 87.166253% of all statistics claim a precision of
results that is not justified by the method employed? [HELMUT RICHTER]
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~



________________________________________________________________________
____________
Looking for a deal? Find great prices on flights and hotels with Yahoo!
FareChase.
http://farechase.yahoo.com/