Re: bivariate animal model with binomial and normal traits
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: bivariate animal model with binomial and normal traits




Dear Maria,
The error you report does not seem to match errors in the nput file.
I include the obvious corrections but there may be more problems.
If this doesn't get you going, please send the .asr file as well as the .as 
file.

Arthur
> 
> 
> Hi users,
> 
> I have had difficults to set up a bivariate animal model with one (0, 1) trait 
(two years-old pregnancy rate) and one normally distributed trait (yearling 
weight).
> 
> - the records of pregnancy rate (females after selection) were obtained for 
1/3 of the total animals wich have records of yearling weight (males and females 
before selection). Can it cause any problem in this kind of bivariate analysis?
> -because of the missing data, I put "9" in the data file to indicate missing 
values for pregnancy rate, and put !m9 in .as file. Can I make this?
> -after run, with sucess, the univariate analysis for weight and p.rate with 
the data file with "9" in the missing values, I make the following .as file to 
run an bivariate analysis:
> 
> Analise de psel e sucesso parto
>  animal !P     #animal
>  mae !I          #dam-to fit permanent environmental effect
>  reb !I            #herd
>  mn !I            # birth month
>  idamae !I      #age of dam
>  sexo !I         #sex
>  idaem !-774.7354    #age at breeding season
>  psel             #yearling weight
>  pren !m9      # p.rate 0 or 1, with missing values =9
> ped_nel.dat
> ptp1.dat  !extra 30 !report
> pren psel !BIN !PROBIT ~ Trait Tr.reb Tr.an at(Tr,1).idaem at(Tr,2).mn 
at(Tr,2).idamae at (Tr,2).sexo !r Tr.animal at(Tr,2).mae 
> 1 2 1
> 0
> 
pren psel !BIN !PROBIT ~ Trait Tr.reb at(Tr,1).idaem at(Tr,2).mn, 
at(Tr,2).idamae at(Tr,2).sexo !r Tr.animal at(Tr,2).mae 
 1 2 1
 0
 Trait 0 US 1 .5 1 !GFP
 Tr.animal 2
 Trait 0 US 0.1 .05 .1 
 animal 0 AINV
 
 
You need to do univariate runs first for both traits to get initial variances.
Then update the values I have placed in this bit of code.

Your model included  Tr.an   which I have dropped as it seems to be a mistake.
It is the same as Trait.animal which appears later.

Your model had an illedal space after 'at' in the sex term.

In the error variance matrix, !GFP fixes the underlying variance for pren at 1.
This is appropriate for !PROBIT.

All the other values will need updating.

Arthur



> 
> Up here, the program failed giving: error setting dependent variable. 
> Moreover I am not sure if  the last two lines are correct, and  how can I to 
indicate the variance and covariance structure.
> 
> Any help will be greatly appreciated
> 
> Maria
> 
> 
> 
> 
> 


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