Prev: Traffic lighting for character variables?
Next: Simple Macro question
From: ManojK on 11 Mar 2010 04:09
On Mar 8, 6:40 pm, iebup...(a)GMAIL.COM ("Data _null_;") wrote:
> On 3/7/10, ManojK <khandelwalmano...(a)gmail.com> wrote:
>
> > I already seen that article but it will not solve my problem.Actually
> > what I want to calculate is by using the MSE values of Model Anova
> > table. I have to use these values in the above mentioned formulas to
> > get my result. But how can I calculate it. There is no simple SAS
> > option so that I get these standard errors for split plot. I have to
> > use IML.
>
> You can use ODS to output the MSEs etc and calculate the SEs if you
> like or you can use PROC MIXED.  LSMEANS /DIFF will show the SEs you
> seek.  Or you can write ESTIMATES statements to do the same thing.
>
> data split;
>    input rep A B yield;
>    cards;
> 1 1 1 25.0
> 1 1 2 31.0
> 1 2 1 21.5
> 1 2 2 24.0
> 2 1 1 41.2
> 2 1 2 36.1
> 2 2 1 40.4
> 2 2 2 37.8
> 3 1 1 26.3
> 3 1 2 32.4
> 3 2 1 28.6
> 3 2 2 27.6
> ;;;;
>    run;
> proc glm;
>    class rep A B;
>    model yield= rep A rep*a B A*B;
>    random rep*a;
>    test h=a e=rep*a;
>    quit;
> data _null_;
>    _1 = sqrt(2*8.5633333/(3*2));
>    _2 = sqrt(2*12.0616667/(3*2));
>    _3 = sqrt(2*12.0616667/3);
>    _4 = sqrt(2*(1*12.0616667+8.5633333)/(3*2));
>    put (_all_)(/=);
>    run;
>
> proc mixed method=type3;
>    class rep A B;
>    model yield= rep A|B;
>    random rep*a;
>    lsmeans a|b / diff;
>
>    ** Can we do it with ESTIMATE;
>    *1. Estimate of S.E. of difference b/w two main plot treatment means =
>        Sqrt(2*E1/r*b)=2*8.5633333/3*2=1.6895;
>    estimate 'Sqrt(2*E1/r*b) main plot' a 1 -1 / e;
>    *2. Estimate of S.E. of difference b/w two sub plot treatment means =
>        Sqrt(2*E2/r*a)=(2*12.0616667/3*2=2.00513;
>    estimate 'Sqrt(2*E2/r*a) sub plot' b 1 -1 / e;
>    *3. Estimate of S.E. of difference b/w two sub plot treatment means at
>        the same level of main plot   treatment = Sqrt(2*E2/r) = 2.8356;
>    estimate 'Sqrt(2*E2/r) same main plot' b 1 -1 a*b 1 -1  / e;
>    *4. Estimate of S.E. of difference b/w two main plot treatment means at
>       the same or different levels of sub plot treatment =
>       Sqrt((2*[(b-1)*E2 + E1])/ r*b) =
> sqrt(2(1*12.0616667+8.5633333))/3*2) 2.62202;
>    estimate 'Sqrt((2*[(b-1)*E2 + E1])/ r*b)' a 1 -1 b 1 -1 / e;
>    run;

Hi data _null_,

Thanks for all such information. I got my result.
But I do not understood Estimate statements. Can you please elaborate
any of one statement. I mean like in 1st statement what this "estimate
'-----' b 1 -1/e;" means?

Thanks once again.

Regards,
Manoj Khandelwal
SRF, IASRI
Delhi
First  |  Prev  | 
Pages: 1 2
Prev: Traffic lighting for character variables?
Next: Simple Macro question