Re: Singularity In Average Information Matrix Using Ainverse

From: Sergio I. Roman Ponce <romanpon77_at_YAHOO.COM>
Date: Thu, 24 Sep 2009 05:48:12 -0700

Dear Dr. Arthur

I am running ASREML 2 but I am having those results. i am warming about the " Singularity in Average Information Matrix".

This is the part of the output:

Forming  734460 equations:  36 dense.
 Initial updates will be shrunk by factor    0.032
 Notice: LogL values are reported relative to a base of -720000.00   
 Notice:      4 singularities detected in design matrix.
 Notice:  1 singularities appeared in Average Information matrix
          This could be a problem of scale or a problem with the model.
          It is preferable to revise the model to remove the singularity.
          Specify !AISING qualifier to force the job to continue.
 Warning:  1 singularities in AI matrix.
 Source                Model  terms     Gamma     Component    Comp/SE   % C
 anim                 341000 341000  0.103237      0.280705      55.44  63 P  
 ide(anim)            341000 341000  0.120000      0.326285       0.00   0 S  
 Variance             692840 640384   1.00000       2.71904     538.43   0 P  
 Warning: Code B - fixed at a boundary (!GP)       F - fixed by user
               ? - liable to change from P to B    P - positive definite
               C - Constrained by user (!VCC)      U - unbounded
               S - Singular Information matrix
 S means there is no information in the data for this parameter.
 Very small components with Comp/SE ratios of zero sometimes indicate poor
           scaling.  Consider rescaling the design matrix in such cases.

 Analysis of Variance              NumDF              F_inc 
   6 MMC                              11             257.14                
  15 DL                               12             529.26                
  11 LACGET                            9             698.30                
   4 HTD                               52424 effects fitted
   1 anim                             341000 effects fitted (  296898 are zero)
  18 ide(anim)                        341000 effects fitted (  296898 are zero)
        4355  possible outliers: see .res file
 Finished: 23 Sep 2009 17:16:56.390   Singularity in Average Information Matrix

Right now i am re-runnig this job with !AISING

How much can affect the results this Singularity in Average Information MatrixRegards,

Sergio Ivan Roman Ponce
Via Sirtori 6, 20129 Milano, Italia
Phone 02/45490025
Mobile +393884496900
Skype: romanpsergio

--- On Thu, 9/24/09, Arthur <asremlforum_at_VSNI.CO.UK> wrote:

From: Arthur <asremlforum_at_VSNI.CO.UK>
Subject: Re: Singularity In Average Information Matrix Using Ainverse
Date: Thursday, September 24, 2009, 1:53 PM

Arthur Gilmour
Received on Fri Sep 24 2009 - 05:48:12 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.)