Re: ANOVA table not in the .ASR file.

Dear Subhash,

I think I understand the problem.

First,
RESPONSE ~ mu GROUP1/ENTRY !r REP REP.GROUP1

is expanded internally to

RESPONSE ~ mu GROUP1 GROUP1.ENTRY !r REP REP.GROUP1

Now if this model has more than 800 levels in mu GROUP1 GROUP1.ENTRY
e.g. 10 groups and a total of 100 entries,

ASReml moves the GROUP1.ENTRY term into the SPARSE section
which is fitted first. Then GROUP1.ENTRY sweeps out all
of the mu and GROUP1 effects so the ANOVA table is empty.
[mu and GROUP1 effects are all singular).

But if the equivalent models
mu GROUP1 ENTRY

or

mu GROUP1 GROUP1.GROUP2 [i.e. mu GROUP1/GROUP2]

are fitted

the total number of columns in the fixed design matrix is less than 800
and so the usual ANOVA is formed.

So, I recommend using
mu GROUP1 ENTRY
as the model

and if there are more than 800 levels (say 1000 ENTRIES)
use the !DENSE qualifier to change the parameter 800 to say !DENSE 2000

On Fri, 2009-03-27 at 09:28 -0500, KRISHNAMURTHY, SUBASH [AG/1000]
wrote:
> Dear Dr. Gilmour,
>
> Thanks for your reply. Actually the levels of GROUP2 are nested within
> the levels of GROUP1. Also, the way the data is constructed is that the
> unique combination of GROUP1 and GROUP2, (let's call it as entry) was
> used in the model instead of the actual levels of GROUP2. What I mean by
> that is if there are 3 levels of GROUP1, with the following levels of
> GROUP2 nested within GROUP1,
>
> GROUP1 GROUP2 ENTRY
> 1 1 1
> 1 2 2
> 1 3 3
> 2 1 4
> 2 2 5
> 2 3 6
> 2 4 7
> 3 1 8
> 3 2 9
> 3 3 10
> 3 4 11
> 3 5 12
>
> The model that did not produce ANOVA table was
>
> tabulate RESPONSE ~ GROUP1 GROUP2
> RESPONSE ~ mu GROUP1/ENTRY !r REP REP.GROUP1
> predict GROUP1 !PRESENT GROUP1 ENTRY!SED !TDIFF
> predict GROUP1.ENTRY !SED !TDIFF
>
> You are correct in that for the above model, the solutions for GROUP1
> effects were all 0.
>
> If I use the following model then everything is fine and all the outputs
> are produced.
>
> tabulate RESPONSE ~ GROUP1 GROUP2
> RESPONSE ~ mu GROUP1/GROUP2 !r REP REP.GROUP1
> predict GROUP1 !PRESENT GROUP1 GROUP2!SED !TDIFF
> predict GROUP1.ENTRY !SED !TDIFF
>
> Best regards,
>
> -Subash
> 314-694-6364
>
> -----Original Message-----
> From: ASReml users discussion group [mailto:ASREML-L_at_DPI.NSW.GOV.AU] On
> Behalf Of arthur.gilmour_at_CARGOVALE.COM.AU
> Sent: Thursday, March 26, 2009 4:28 PM
> To: ASREML-L_at_DPI.NSW.GOV.AU
> Subject: Re: ANOVA table not in the .ASR file.
>
> Dear Subhash,
>
> I am surprised the ANOVA table is completely missing for the model you
> propose. If the levels of GROUP1 were nested in the levels of GROUP2
> (nested within mu), then fitting GROUP1 (ahead of GROUP2) would sweep
> out
> the GROUP2 DF and so the line in the ANOVA for GROUP2 will be missing.
> You can look in the .sln file and see all the GROUP2 effects are zero,
> and there is more ANOVA information in the .aov file which shpuld make
> it
> clearer what will happen.
>
> The only reason all terms would disappear from the ANOVA table is if
> there is a fixed effect fitted as SPARSE which sweeps out all the DF.
>
> Consider sites nested within localities
>
> S1 and S2 in L1
> S3 S4 S5 in L2
>
> res ~ mu Loc Site !r Rep.Site
>
> should produce ANOVA
>
> mu 1
> Loc 1
> Site 3
>
>
> but
>
> res ~ mu Site Loc !r Rep.Site
>
> should produce ANOVA
>
> mu 1
> Site 4
>
> and
>
> res ~ mu Loc !r Rep.Site !f Site
>
> should produce no lines in the ANOVA table
> because all 5 DF are swept out in the SPARSE section.
>
> The table heading should be present though.
>
> I trust this helps
>
> If you really do have a job woth NO ANOVA table, but which finished
> properly, I need to see it.
>
> > Hello,
> >
> >
> >
> > I am using ASREML to analyze data from a Group Un-balanced Block
> design
> > and noticing that the ANOVA table is missing from the .ASR file. The
> > ASREML model statement is as shown below. Does anyone know of any
> > qualifiers that forces ASREMP to produce the ANOVA table in the
> output?
> > Also, what is the reason for the ANOVA table to be missing?
> >
> >
> >
> > tabulate RESPONSE ~ GROUP1 GROUP2
> >
> > RESPONSE ~ mu GROUP1/GROUP2 !r REP REP.GROUP1
> >
> > predict GROUP1 !PRESENT GROUP1 GROUP2 !SED !TDIFF
> >
> > predict GROUP1.GROUP2 !SED !TDIFF
> >
> >
> >
> >
> >
> > Thanks in advance for your response.
> >
> >
> >
> > Best regards,
> >
> > -Subash
> >
> > 314-694-6364
> >
> >
> >
> ------------------------------------------------------------------------
> ---------------------------------
> > This e-mail message may contain privileged and/or confidential
> > information, and is intended to be received only by persons entitled
> to
> > receive such information. If you have received this e-mail in error,
> > please notify the sender immediately. Please delete it and all
> attachments
> > from any servers, hard drives or any other media. Other use of this
> e-mail
> > by you is strictly prohibited.
> >
> >
> > All e-mails and attachments sent and received are subject to
> monitoring,
> > reading and archival by Monsanto, including its subsidiaries. The
> > recipient of this e-mail is solely responsible for checking for the
> > presence of "Viruses" or other "Malware". Monsanto, along with its
> > subsidiaries, accepts no liability for any damage caused by any such
> code
> > transmitted by or accompanying this e-mail or any attachment.
> >
> ------------------------------------------------------------------------
> ---------------------------------
> >
> >
> > 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.
> >
>
> 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.
>
>
>
> ---------------------------------------------------------------------------------------------------------
> This e-mail message may contain privileged and/or confidential information, and is intended to be received only by persons entitled to receive such information. If you have received this e-mail in error, please notify the sender immediately. Please delete it and all attachments from any servers, hard drives or any other media. Other use of this e-mail by you is strictly prohibited.
>
>
> All e-mails and attachments sent and received are subject to monitoring, reading and archival by Monsanto, including its subsidiaries. The recipient of this e-mail is solely responsible for checking for the presence of "Viruses" or other "Malware". Monsanto, along with its subsidiaries, accepts no liability for any damage caused by any such code transmitted by or accompanying this e-mail or any attachment.
> ---------------------------------------------------------------------------------------------------------
>

-- 
May the God and Father of the Lord Jesus Christ guide and bless you.
Arthur Gilmour
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:
Katoomba 13-15 March
USA  1-11 April
Brazil/UK July/Aug ??