Re: probably a simple problem
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: probably a simple problem



DEar Rob,

I do not understand why the .asr file is empty unless ASREML is crashing.

Your model line is wrong but I'm not sure exactly what you intend.

Try the following


analysing heritability of preference for orange
 Sire 40
 Dam 3
 Por
fems.dat !skip1
 Por ~ mu !r Sire Dam
 
This job implies that the file  fems.dat has three columns
 the first column contains Sire codes (number 1...40)
 the second column contains dam codes numbered 1...3
 the third column is the dependent variable Por
 [There may be extra columns which would be ignored]
 
 I do not understand the Dam column.  Do you have 40 sires mated to 3 Dams
 [unlikely for animals, possible for trees]
 Or is Dam acturally dam breed?
 
 Anyway,  the model needs to have a mean in it (hence mu)
 and as a variance components model needs to declare Sire as random.
 Depending on what Dam means, it should either be omitted (if
 Sire.Dam == Error), or maybe treated as fixed (mu Dam !r Sire) or
 as random (mu !r Sire Dam)
 
 Oh  I see you have included the data.
 
 I ran the job as you sent it.  It worked for me
 fitting  Sire.Dam and Sire as fixed effects.
 
 I then inserted  mu !r
 
 to fit   Por ~ mu !r Sire Sire.Dam and got the following
 which I presume is what you want.
 
 If running the SUN version, it may be crashing because you are
 not on an X windows terminal or have killed the graphics rather than
 pressing Esc  and letting ASREML finish.
 
 You can suppress graphics by typing     ASREML -n fems
 to run the job.
 
 Arthur
 
   ASREML [25 Mar 1999]  analysing heritability of preference for orange                         
 Fri Mar 26 08:41:37 1999 144.00 Mbyte    fems
 QUALIFIERS: !skip1                                                      
  Reading fems.dat  FREE FORMAT skipping 1 lines
 Univariate analysis of Por                 
 Using      299 records [of     299 read from     299 lines of fems.dat          
  ]
  Model term      Size Type    COL   Minimum    Mean      Maximum   #zero #miss
   1 Sire           40 Factor    1      1    21.5217         40         0     0
   2 Dam             3 Factor    2      1     1.8896          3         0     0
   3 Por             1 Variate   3 -128.1      3.878      131.2         0     0
   4 mu              1 Constant Term
   5 Sire.Dam      120 Interaction  1 Sire    :   40    2 Dam            :    3
  Forming 162 equations: 2 dense
 Initial updates will be shrunk by factor    0.548
 NOTICE:    24 (more) singularities,
 LogL=-1096.81     S2=  493.17        298 df  0.10000    0.10000     1.0000    

 LogL=-1096.50     S2=  495.17        298 df  0.62814E-010.11852     1.0000    

 LogL=-1096.42     S2=  495.74        298 df  0.37973E-010.13656     1.0000    

 LogL=-1096.42     S2=  495.29        298 df  0.33919E-010.14153     1.0000    

 Final parameter values                       0.33422E-010.14206     1.0000    


   Source               Model  terms     Gamma     Component    Compnt/StndErr 
%C
  Sire                     40     40  0.334218E-01   16.5535          0.51  -1 P  
  Sire.Dam                120     96  0.142060       70.3610          1.52   0 P  
   Variance               299    298   1.00000       495.290         10.22   0 P  
                     Solution       Standard Error    T-value     T-prev
   4 mu                       1        5.31        5.31             [DF F_inc 
F_all]
                    1    3.95049        1.71516          2.30
   1 Sire                    40 effects fitted
   5 Sire.Dam                96 effects fitted
 5 possible outliers: see .res file
 Finished: Fri Mar 26 08:41:38 1999   LogL Converged                                              

  
 
 
> X-Authentication-Warning: lamb.chiswick.anprod.csiro.au: petidomo set sender 
to asreml-owner@ram.chiswick.anprod.csiro.au using -f
> Mime-Version: 1.0
> Date: Thu, 25 Mar 1999 15:30:40 +1100
> To: asreml@ram.chiswick.anprod.csiro.au
> From: Rob Brooks <rob.brooks@jcu.edu.au>
> Subject: probably a simple problem
> 
> Hi,
> 
> I am wondering if anybody can help me as I seem to be in a bit over my head.
> I want to analyse the results from a simple halfsib experiment. As there
> have been quite a few deaths, my design has become decidedly unbalanced, and
> I am getting some pretty strange estimates of variance components from
> nested ANOVA. Hence my desire to estimate these components using REML and my
> attempts to do this using ASREML. 
> 
> When I try to run what I think is the right model, the .asr file comes up
> empty. I am afraid my knowledge is not good enough to understand the section
> on variance model specification (p 63 of the manual) well enough to know
> what is going wrong. Is there something glaringly missing from the job file
> below, that is leading to my inability to estimate the required variance
> components?
> 
> analysing heritability of preference for orange
>  Sire 40
>  Dam 3
>  Por
> fems.dat !skip1
>  Por ~ Sire Sire.Dam
> 
> I would appreciate if tremendously if anyone who has experience using ASREML
> for these admittedly simple types of analysis could point me in the right
> direction.
> 
> Best,
> 
> Rob Brooks
> 
> 
> the data file reads as follows .... 
> 
> Sire    Dam     Porrat

> ___________________________
> School of Tropical Biology 
> James Cook University      
> Townsville 4811
> Queensland, Australia
> 
> ph: +61-7-4781-4485
> fax: +61-7-4725-1570
> 
> --
> Asreml mailinglist archive: http://www.chiswick.anprod.csiro.au/lists/asreml


<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>
Arthur Gilmour PhD                    mailto:Arthur.Gilmour@agric.nsw.gov.au
Senior 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

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

                        <> <> <> <> <> <> <>
"You (Father) have given Him (Your Son) authority over all flesh,
   that He should give eternal life to as many as You have given Him.
And this is eternal life,
   that they may know You, the only true God,
   and Jesus Christ whom You have sent."  John 17: 2-3.
<><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>


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