Re: Defining structure of residual variance
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Defining structure of residual variance



Dear Jørgen

You will need to sort your data file on period so that the first
#1 records are period 1
#2 records are period 2 etc
and know what the numbers #1 #2 ... #10 are.

Also, let #V represent the variance from the model you have fitted
being an initial value for the separate variances.

Then replace the

0 0 2  line
with

10 1 2
#1 0 0 !S2=#V
#2 0 0 !S2=#V
#3 0 0 !S2=#V
#4 0 0 !S2=#V
#5 0 0 !S2=#V
#6 0 0 !S2=#V
#7 0 0 !S2=#V
#8 0 0 !S2=#V
#9 0 0 !S2=#V
#10 0 0 !S2=#V


Finally, you will have to change the 4 'variance' parameterts
in the CORR structures from being variance ratios
to being actual variances by multiplying them by #V

However, there could be problems fitting this model
if there are big differences in error variance becasue the 'average'
values of the genetic variance might try and force some of the error
variances negative!.  You understand the data structure and I do not
but I am saying - make sure the model is sensible.

Arthur

> X-Authentication-Warning: lamb.arm.li.csiro.au: petidomo set sender to 
asreml-owner@lamb.arm.li.csiro.au using -f
> From: Jørgen Ødegård <ihfjo@ihf.nlh.no>
> To: <asreml@chiswick.anprod.csiro.au>
> Subject: Defining structure of residual variance
> Date: Thu, 30 Aug 2001 10:37:00 +0200
> MIME-Version: 1.0
> Content-Transfer-Encoding: 8bit
> 
> Hi,
> 
> I am currently working on a RR model for SCC in dairy cattle. I want to use
> a model with different residual variances in different parts of the
> lactation, but don't know how to do it.
> 
> I separate the lactation in 10 periods. The program file looks as follows
> (simplified):
> 
> Random Regression Sire Model
> 
>   sire       566 !P
>   pe       95009
>   period      10      #Period of lactation
>   leg0                #Legendre polynomials
>   leg1
>   leg2
>   leg3
>   scs                 #Dependent variable
> 
> srrm1.ped !MAKE
> srrm1.dat !MAXIT 40
> 
> scs ~ leg0 leg1 leg2 leg3 !r leg0.sire leg1.sire leg2.sire leg3.sire leg0.pe
> leg1.pe leg2.pe leg3.pe
> 
> 0 0 2
> leg0.sire 2
> 4 0 CORR 0.7849E-01 !+9 !GP
> -0.1147 0.7774
> 0.1641 -0.7713 -0.9849
> 0.1142 0.3085E-01 0.2090E-01 0.1054E-01
> leg0.sire 0 0
> 
> leg0.pe 2
> 4 0 CORR 0.1047 !+9 !GP
> -0.4579 0.7774
> 0.2754 -0.1683 -0.5954
> 3.084 0.3992 0.1963 0.8589E-01
> leg0.pe 0 0
> 
> How can I mdoify this program to estimate different residual variance in
> each period? (A diagonal matrix)
> 
> Thanks in advance
> 
> ************************************
> Jørgen Ødegård
> Department of Animal Science
> Agricultural University of Norway
> PO box 5025
> N-1432 Aas
> Norway
> Phone: +47 6494 7998
> E-mail: jorgen.odegard@ihf.nlh.no
> 
> --
> Asreml mailinglist archive: http://www.chiswick.anprod.csiro.au/lists/asreml


<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>
Arthur Gilmour PhD                  mailto:Arthur.Gilmour@agric.nsw.gov.au
Principal Research Scientist (Biometrics)            fax: <61> 2 6391 3899
NSW Agriculture                                           <61> 2 6391 3922
Orange Agricultural Institute             telephone work: <61> 2 6391 3815
Forest Rd, ORANGE, 2800, AUSTRALIA                  home: <61> 2 6362 0046
                                                   Cargo: <61> 2 6364 3288
I havn't finished building my house at Cargo but am back at work.

ASREML is still free by anonymous ftp from pub/aar on ftp.res.bbsrc.ac.uk
    or point your web browser at ftp://ftp.res.bbsrc.ac.uk/pub/aar/ 

To join the asreml discussion list, send the message  
     subscribe
mailto:asreml-request@chiswick.anprod.CSIRO.au

To send messages to the list, mailto:asreml@chiswick.anprod.CSIRO.au

Asreml list archive: http://www.chiswick.anprod.csiro.au/lists/asreml

                        <> <> <> <> <> <> <>
"Blessed are the peacemakers,
        for they shall be called sons of God"   Jesus; Matthew 5:9

<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>





--
Asreml mailinglist archive: http://www.chiswick.anprod.csiro.au/lists/asreml