| vector t-test? [message #36821] |
Mon, 03 November 2003 07:19  |
wmconnolley
Messages: 106
Registered: November 2000
|
Senior Member |
|
|
Can I do a t-test on vectors (I mean, where each data point is a 2-d
vector)? tm_test says it works on reals; does it work on complex
data?
-W.
--
William M Connolley | wmc@bas.ac.uk | http://www.antarctica.ac.uk/met/wmc/
Climate Modeller, British Antarctic Survey | Disclaimer: I speak for myself
I'm a .signature virus! copy me into your .signature file & help me spread!
|
|
|
|
| Re: vector t-test? [message #36912 is a reply to message #36821] |
Mon, 03 November 2003 11:16  |
mmiller3
Messages: 81
Registered: January 2002
|
Member |
|
|
>>>> > "wmc" == wmc <wmc@bas.ac.uk> writes:
> Can I do a t-test on vectors (I mean, where each data point
> is a 2-d vector)? tm_test says it works on reals; does it
> work on complex data?
No - a t-test compares the means of two populations. If you have
multidimensional data, you can compare means along multiple axes.
Those may not be orthogonal though (even if the axis are
spatially orthogonal), so the results may not be independent.
To get a better measure of the difference between the two
populations, take a look at various spatial statistics methods to
find the "right" statistic for your use. I don't know what is
available in IDL though...
Regards, Mike
--
Michael A. Miller mmiller3@iupui.edu
Imaging Sciences, Department of Radiology, IU School of Medicine
|
|
|
|
comp.lang.idl-pvwave archive
Members
Search
Help
Login
Home
