Re: Repeated measurements in R structure

Dear Ruben,

With just 3 time points, I would probably organize the data
as multivariate and use a US structure in the first instance.

But it should be possible to analyse with the data as you appear to have
it.

So, you say you have 5 sites by 3 reps by 3 times by 107 genotypes,
a total of 4815 observations.

Therefore the R structure(s) must define 4815 records!
But you have given an R stucture for 107 lots of 3!

Then, when ASReml reads the first 321 records and attempts to sort them
as 107 lots of 3 repeats, it only finds numbers 1:8 in the genotype
field. Maybe the data is sorted with genotype as the outer factor so
that the first 321 records just covers the first 7 genotypes and part of
the 8th.

The R structure you have defined assumes repeated.csv has 321 records,
and is for 1 replicate, and 1 site

This is obviously not true since the output seems to report 395 missing
values in the response. The reported output does not match the alleged
input.

!MVREMOVE is not apporpriate if you are define a direct product R
structure. Either it is unnecessary because every record has Geno,
Time, Rep, and Site defined, or it will discard records where these are
not defined, and the R structure will be thrown out of kilter.

Now if you sorted the data on the first 4 fields (assumng 4815 records),
you could use the following code (and there are many possible
variations)

Yield ~ mu Loc Time !r Loc.Rep Gen !f mv
1 2 0
1605 !S2==1
3 0 US !GP
1 .1 1 .1 .1 1 #put these on an appropriate scale.

I trust that helps you get a little further.

On Tue, 2009-11-10 at 13:08 +0000, Ruben wrote:
> Dear group,
> I’m struggling with the analysis stated below. Any help would be
> highly appreciated.
> Many thanks in advance for your time, and sorry for my limited
> knowledge of ASReml
> Ruben
>
> Analysis goal
> I have 107 genotypes (Gen) measured (for Yield) at 3 different time
> points -1,2,3, equally spaced- (Time) with 3 replicates at each
> Gen/time combination. Another variable in my dataset is location (LOC
> with 5 levels), plus others not participating in the analysis
> P7,X,XM,Xmn,PT
> I want carry out a ‘repeated measurement’ analysis as if it was a
> ‘spatial analysis in one dimension’, this means, specify different
> correlation/covariances between time points across genotypes in the R
> matrix and not in G. Is it possible? I have problems, according to the
> asr error message, to sort data into field order. Please let me know
> if I’m out of track on the following:
>
> AS used
> Repeated
> Loc !A 5
> Gen !A 107
> Rep 3
> Time 3
> Yield
> P7
> X
> XM
> Xmn
> PT
>
> Repeated.CSV !MAXIT 50 !MVREMOVE !SKIP 1
>
> Yield ~ mu Time !r Gen !f mv
> 1 2 0
> 107 Gen ID
> 3 Time AR1 0.1
>
> ASR with error statement:
> 91 mv_estimates 395
> 107 identity
> 3 AR=AutoReg 0.1000
> Warning: Spatial mapping information for side 1 of order 107
> ranges from 1.0 to 8.0
> Error: Failed to sort data records: Sortkeys
> ***************
> ***************
> ***************
> ***************
> ***************
> ***************
> ***************
> ***************
> ***************
> ***************
> Fault 2 Sorting data into field order
> Last line read was: 3 Time AR1 0.1 0 0 0 0 0
> Dummy LOC,GENOTYPE,REP,Time, P4,P7,X,XM,Xm,PT
> Model specification: TERM LEVELS GAMMAS
> Time 3
> mu 1
> Gen 107 0.100 [ 3]
> mv_estimates 395
> SECTIONS 321 5 1
> STRUCT 107 0 0 0 0 1 2
> 3 1 1 6 1 1 4
> 91 factors defined [max 500].
> 6 variance parameters [max1500]. 2 special structures
> Final parameter values [ 3: 6] 0.10000 0.0000 -.10000E-36
> 0.10000
> Last line read was: 3 Time AR1 0.1 0 0 0 0 0
> 91 2 4815 4815 158000
> Finished: 10 Nov 2009 12:17:34.345 Sorting data into field order
>
>
>
>
> -------------------- m2f --------------------
>
> Sent using Mail2Forum (http://www.mail2forum.com).
>
> Read this topic online here:
> http://www.vsni.co.uk/forum/viewtopic.php?p=1004#1004
>
> -------------------- m2f --------------------
>
>
>
>
> This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender, and are not necessarily the views of their organisation.

-- 
Best Wishes,
Arthur Gilmour
Adjunct Professor
School of Computing and Mathematics
Charles Sturt University
Jesus went to the synagogue in every town in Galilee to preach and drive
out demons.
A leper came, knelt down and said, "If you will, you can make me clean".
Jesus was moved. He reached out and touched him and said 
"I am willing.  Be clean." He was cleansed immediately.
Mobile Number +61 427 227 468
Home phone +61 2 6364 3288  Skype: Arthur.Gilmour
http://www.CargoVale.com.au/asreml
By the way: listen to Alan Jones (2GB Radio) interview 
with Lord Mockton on the Copenhagen Summit 
http://2gb.com.au/index2.php?option=com_newsmanager&task=view&id=4998 
Travel:
Brisbane Probe 29Nov to 6 Dec
Bangladesh Proshikkon 31Dec - 6 Feb