Re: ASREML output vs SAS output

Dear Mr edeomano(?)

you wrote

Here are the codes/model I used and corresponding output:

ASREML MODEL: Weight ~ Clone !r Rep
ASREML OUTPUT:
- - - Results from analysis of Weight - - -
Approximate stratum variance decomposition
Stratum Degrees-Freedom Variance Component Coefficients
Rep 1.00 46241.7 10.0 1.0
Residual Variance 19.00 5379.58 0.0 1.0

Source Model terms Gamma Component Comp/SE % C
Rep 1 1 0.759547 4086.04 0.62 0 P
Variance 40 20 1.00000 5379.58 3.08 0 P

Wald F statistics
Source of Variation NumDF DenDF F_inc Prob
1 Clone 20 18.7 3.16 0.008

SAS CODE:
proc mixed data=data1 method=reml;
class rep clone;
model weight=clone;
random rep;
SAS OUTPUT:
The Mixed Procedure
Covariance Parameter
Estimates
Cov Parm Estimate
Rep 2043.02
Residual 5379.58

Type 3 Tests of Fixed Effects
Num Den
Effect DF DF F Value Pr > F
Clone 19 19 1.19 0.3526

*****************
my reply

1. It is very hard to tell without the asreml job and the data
2. the REML estimate of rep variance for ASreml appears to be 2*SAS value
3. There appears to be 20 df for Clones in the ASReml job but 19 for SAS.
I gather it is a trial with 2 reps
4. perhaps send the asreml job and I may be able to help resolve this for
you

HTH

warm regards

Brian Cullis|Research Leader, Biometrics &
Senior Principal Research Scientist |
Industry & Investment NSW | Wagga Wagga Agricultural Institute | Pine
Gully Road | Wagga Wagga NSW 2650 |
PMB | Wagga Wagga NSW 2650
T: 02 6938 1855 | F: 02 6938 1809 | E: brian.cullis_at_industry.nsw.gov,au
W: www.industry.nsw.gov.au |

Visiting Professorial Fellow
School of Mathematics and Applied Statistics
Faculty of Informatics
University of Wollongong

Professor,
Faculty of Agriculture, Food & Natural Resources
The University of Sydney

Adjunct Professor
School of Computing and Mathematics
Charles Sturt University
 
Received on Sat Sep 18 2009 - 11:27:44 EST