Re: SE fo constrain 'sum to zero' fixed effect

From: Arthur Gilmour <arthur.gilmour_at_CARGOVALE.COM.AU>
Date: Fri, 24 Apr 2009 14:56:57 +1000

Dear Vivi,

There is no simple way.

Assuming the term in question is fitted in the first (fitted dense)
part of the model, you could use the !VRB qualifier to extract the
variance matrix for the fixed effects. Then the variance of the missing
effect is the variance of the sum of the terms actually fitted. E.g.
It there is a total of 4 levels (A B C D), you will be able to extract
the variance matrix for (A-mu, B-mu, C-mu) a 3x3 matrix symbolically
represented by

AA
AB BB
AC BC CC

The variance of D-mu is AA+BB+CC+2AB+2AC+2BC

Alternatively, you could use a predict statement like

PREDICT !AVE c(FACTOR) -1 -1 -1 !ONLY c(FACTOR) !PRINTALL

or some variation of that.
!PRINTALL is required because this is not 'an estimable function'

Many statisticians dislike looking at such effects and consider it is
more sensible to look at estimable contrasts such as D vs
average(A,B,C)

On Thu, 2009-04-23 at 20:32 -0700, vivi noviati wrote:
> Dear All,
>
> Please excuse my question, but I am wondering how to get SE for the
> last term in fixed effect when it was constrain to sum to zero using
> c(f).
>
>
> Thank you.
>
> Regards,
> Vivi
>
>
>
>
>
>
> This message is intended for the addressee named and may contain confidential information. If you are not the intended recipient, please delete it and notify the sender. Views expressed in this message are those of the individual sender, and are not necessarily the views of their organisation.

```--
May the God and Father of the Lord Jesus Christ guide and bless you.
Arthur Gilmour
PS Are you anxious?
http://www.aish.com/spirituality/growth/God_vs._Prozac.asp
Mobile Number +61 427 227 468
Home phone +61 2 6364 3288  Skype: Arthur.Gilmour
http://www.CargoVale.com.au
Wisdom is justified by all her children  Luke 7:35
Travel:
Tas 11-16 May
Brazil Jul27 - Aug 8
UK Aug 10-14
```
Received on Sat Apr 24 2009 - 14:56:57 EST

This webpage is part of the ASReml-l discussion list archives 2004-2010. More information on ASReml can be found at the VSN website. This discussion list is now deprecated - please use the VSN forum for discussion on ASReml. (These online archives were generated using the hypermail package.)