Hi All-
I'm responding here to Jess's question below, I don't have a direct
e-mail for Jess to respond off-line.
Tne IMP CVAGen pogram does output the PW scores in the same format as
PCAGen. I need to update the CVAGen manual.
As long as the subject has come up, would users find it helpful to have
a header line in the file, labeling each column of the output? I did
not put this in original version, as it seemed easier to import the file
into other programs if it did not have the header. Does anyone have any
comments? Headers or no?
-Dave
H. David Sheets, PhD
Dept of Physics, Canisius College
2001 Main St
Buffalo NY 14208
---- Original message ----
Date: Wed, 07 Jun 2006 13:56:04 -0400
From: morphmet <[EMAIL PROTECTED]>
Subject: IMP Question
To: [email protected]
Hello group --
Please forgive my relatively simplistic question, but my working group
is looking for a quick confirmation on a question regarding IMP. We are
using the CVA portion of the software package, and we wanted to confirm
that, like the PCA portion, the partial warp scores are reported in the
output in the following order (with a hypothetical 4 components, uniform
components, and centroid):
X4 Y4 X3 Y3 X2 Y2 X1 Y1 UNIX UNIY CS
(there has been some confusion within our group with some thinking that
the order in the output of warp scores would be X1 Y1 X2 Y2 X3 Y3 X4 Y4
UNIX UNIY CS).
A quick off-line email would be SO appreciated...again, I apologize for
the rather simplistic question, but we wanted to confirm the correct
assignment of the PWs in the output generated by IMP.
Thank you!
Cheers,
Jess White
Western Illinois University
Department of Sociology and Anthropology
_________________________________________________________________
On the road to retirement? Check out MSN Life Events for advice on how to
get there! http://lifeevents.msn.com/category.aspx?cid=Retirement
--
Replies will be sent to the list.
For more information visit http://www.morphometrics.org
--
Replies will be sent to the list.
For more information visit http://www.morphometrics.org
