Re: data format for multivariate analysis

From: Arthur Gilmour <arthur.gilmour_at_AGRIC.NSW.GOV.AU>
Date: Fri, 20 May 2005 14:09:31 +1000

Dear Chandra

** I am inclined to think you should try and treat the situation as being
of 6 traits
assuming the repeated traits relate to two specific lambings - i.e.
WT LS F1 F2 lit1 lit2

Hoever I do not understand what the variable LAMBSURVIVAL is in this
context. I assume the data is of ewes who have had two lambings
so obviously they have all survived as lambs. So does lamb survival
relate to all the lambs born across the two litters?

Anyway, with six traits, you would then want to apply some constraints so
that say
F1 and F2 had the same variances and lit1 and lit2 had the same variances.

You wrote
Thank you for the quick response. My two repeated traits are 'fertility'
and 'live litter size' while the single measure traits are '3-month
and 'lamb survival'. So there is an association between the repeated
and perhaps between 'litter size' and 'lamb survival' but not really
between the repeated traits and '3-month weight'. What would be the best
way to arrange the data in this case?

Not sure I understand what you mean by treating 4 traits as six traits. Do
you mean having the repeat measurements in separate columns?

Regards, Chanda

At 12:32 PM 5/20/2005, you wrote:
>Dear Chanda,
>What you propose is commonly done but may not always be best.
>It depends on the relationship between the traits; another way would be
>treat the
>4 traits as six traits. The point is whether it is obvious which of the
>repeated trait values,
>the unrepeated trait is associated with. You need to make sure you allow
>the repeatability
>in the model.

with God's love in the Name of Jesus Christ.
Check out

Arthur Gilmour PhD
Principal Research Scientist (Biometrics)
NSW Department of Primary Industries
Orange Agricultural Institute, Forest Rd, ORANGE, 2800, AUSTRALIA
fax: 02 6391 3899; 02 6391 3922 Australia +61
telephone work: 02 6391 3815; home: 02 6364 3288; mobile: 0438 251 426
The ASReml discussion group
   has reactivated. To join,

Proposed travel:
Des Moines USA 23-27 May
St Louis M, USA 31-3 Jun
Rothamsted UK 6-22 June

This message is intended for the addressee named and may contain
confidential information. If you are not the intended recipient or
received it in error, please delete the message and notify sender. Views
expressed are those of the individual sender and are not necessarily the
views of their organisation.
Received on Thu May 20 2005 - 14:09:31 EST

This webpage is part of the ASReml-l discussion list archives 2004-2010. More information on ASReml can be found at the VSN website. This discussion list is now deprecated - please use the VSN forum for discussion on ASReml. (These online archives were generated using the hypermail package.)