Re: R-structure
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: R-structure




>
> 
> Hi ASREMLers!
> Any suggestions about these two problems? 
> 
> 1. A question about the structure of the residual (R).
> I have individual data of feed intake of approx. 3000 pigs at the 25 days
> 3,4,5,6,7, 17-21, 31-35, 45-49 and 59-63. I would like to try heterogeneous
> AR and heterogeneous ARMA for these data, so that R(ARH)=
>  
> a.a a.b.r a.c.r2 a.d.r3 a.e.r4      (~0)         ...
>     b.b   b.c.r  b.d.r2 b.e.r3
>           c.c    c.d.r  c.e.r2
>      (sim)       d.d    d.e.r
>                         e.e   
>                                f.f f.g.r f.h.r2  ...
>                                    g.g   g.h.r   ...
>                                          ...     ...
> 
> How could I do that? Perhaps using 'POW'? Gamma results using DIAG were:
> 1.18 0.91 1.00 0.98 1.09
> 1.21 1.22 1.20 1.22 1.35
> 1.44 1.45 1.46 1.31 1.35
> 1.66 1.72 1.67 1.52 1.63
> 1.96 1.95 1.80 1.64 1.76

You can fit an AR type structure using actual times using

25 0 EXPH .5
 1.18 0.91 1.00 0.98 1.09
 1.21 1.22 1.20 1.22 1.35
 1.44 1.45 1.46 1.31 1.35
 1.66 1.72 1.67 1.52 1.63
 1.96 1.95 1.80 1.64 1.76
 
 3 4 5 6 7 17 18 19 20 21 31 32 33 34 35 45 46 47 48 49 59 60 61 62 63
 
 
 Where the last line specifies the distances.  However, the autocorrelation on 
this scale
 might be very high in which case you may need to scale the distances e.g.
 .75 1 1.25 1.5 ...      to get phi (the correlation parameter) a reasonable 
value.
 
 
 There is no way of fitting and ARMA or MA structure when distiance are not
 1 ... n
 
 
> 2. Is the G matrix correct as follows or should I modify it according to the
> data structure?
> 
> fi~ mu !r ident ident.x ident.x2 !f mv
> 
> 0 0 1
> 
> ident 2
> 3 0 US !+6
> 0.03681
> 0.001 0.08332
> 0.001 0.001 0.08332
> ident 0 AINV
> 
>

This syntax is correct though for this univariate analysis, you could omit !f mv

Arthur  
> 
>  			                                                                     
>   Justo Lorenzo Bermejo                                    
>   Institut fr Tierzucht und Tierhaltung                   
>   Olshausenstr. 40                                           
>   24118 Kiel  	                                             
>   Germany                                    &_____         
>                                              /     ^..^     
>   T.n. 0431  880 7315                        \_____(oo)    
>   Fax  04340 402 761                          WW WW        
>   jlorenzo@tierzucht.uni-kiel.de                           
>                                                            
> 
> 
>           La vida est hecha solo de momentos
> 
> --
> 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

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