Re: using predict statement
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: using predict statement




> 
> Hi,
> 
> I'm starting to use the predict statement, but I'm not sure about how
> does it work. Using a model like:
> 
> !part 13
> PPY ~ mu subrace rep !r mother
> 0
> predict subrace
> 
> I obtain results for subraces like:
>  rep                  is averaged over fixed levels
>  Predicted values of PPY
>  mother               is ignored in the prediction

Note the above comment:  You would get different (smaller) standard errors if
the prediction averaged over mother by saying
  predict subrace !ave mother
  
  .  If mother was nested within subrace, you would need to say
  predict subrace !present mother subrace
  
>  WARNING:  Missing cells in table
     Can you see what is missing? were there more subraces?

> 
>  subrace             Predicted_Value Standard_Error EPcode                                   
>  "Flinders Island"           51.1017         0.4593 P  
>  "King Island"               51.7799         0.4051 P  
>  "Strzelecki Ranges"         51.2644         0.4696 P  
>  "Southern Tasmania"         52.0033         0.4782 P  
>  "Western Otways"            52.2484         0.4108 P  
>  "North-eastern Tasma        50.5914         0.6675 P
>  "South-eastern Tasma        51.9727         0.3643 P  
>  "Strzelecki Foothill        50.7930         0.4653 P  
>  Standard Error of Difference: Min     0.5433   Mean     0.6613   Max     
0.8188
> 
> From the as file mu is 50.4851 with sdterr 0.490574. Shouldn't some of
> the subrace solutions be over and some under the overall mean? That is
> the case if I calculate mu+subrace effects (either from the .asr or
> the .sln files). I would appreciate an explanation about how does
> predict work.

  Leave  mu  out of the model and see if you get the same prediction.
  Averaging over rep is probably causing the confusion.  The fitted mu
  relates to a rep_1 effect of zero  while the predicted values
  relate to an average rep effect of zero.  i.e.  the difference between what 
you calculated
  from the .sln file and what asreml gives in the pvs file should be
  the average rep effect.
  
  Arthur
> 
> Best regards,
> 
> 
> Luis
> 
> -- 
> Dr Luis A. Apiolaza
> Quantitative Geneticist
> CRC for Sustainable Production Forestry
> School of Plant Science
> University of Tasmania
> GPO Box 252-55
> Hobart TAS 7001
> Australia
> 
> phone:   +61-3-6226 2213
> fax:     +61-3-9229 2698
> email:   mailto:luis.apiolaza@utas.edu.au
> 
> 'The search for truth is more precious than
>  its possession' --Albert Einstein
> http://www.scieng.utas.edu.au/plantsci/
> http://www.geocities.com/uncronopio/
> ;-)
> 
> --
> 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 6364 3288
                                                  mobile: <61> 4 1964 7675
ASREML is available 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