AW: problem of estimation VC[Scanned.]

Hi Jiqiu,

sorry, I didn't read the email completely. You have simulated the data of 10000 animals. But nevertheless I think your estimates are quite good.

Dörte

-----Ursprüngliche Nachricht-----
Von: Wittenburg, Dörte
Gesendet: Mo 10.12.2007 11:18
An: ASReml users discussion group
Betreff: AW: problem of estimation VC[Scanned.]

Hi Jiqiu,

your results base on a simulation with 10 animals only. Thus, your estimates are really good!
You may repeat your simulation and the run in ASReml e.g. 100 times, then you calculate the averages of estimated variance components and sex effect. These averages should be closer to the simulated components.

Cheers, Dörte

~~~~~~~~~~~~~~~~~~~~~~~~~~
FBN Dummerstorf
Genetics & Biometry
Wilhelm-Stahl-Allee 2
18296 Dummerstorf, Germany
~~~~~~~~~~~~~~~~~~~~~~~~~~

-----Ursprüngliche Nachricht-----
Von: ASReml users discussion group im Auftrag von Jiqiu Cheng
Gesendet: Mo 10.12.2007 10:37
An: ASREML-L_at_AGRIC.NSW.GOV.AU
Betreff: problem of estimation VC[Scanned.]

Quoting arthur.gilmour_at_DPI.NSW.GOV.AU:
Dear sir,
   I simulate the records including fixed effect "sex", direct genetic
effect (d), competitive genetic effect (c) from penmates and
independent residual(e). Then I use ASREML to estimate the variance
components. The estimation of variance components and fixed effect
show some deviation from the true parameters.
   My question is whether the code I used to estimate the model in
ASREML is correct? If it is correct, are there some solutions to
improve the estimation?

Thank you very much for your help.
Best regards,
Jiqiu

The model of simulation:
y1=sex(+d+c2+c3+c4+e1

The parameter of simulation:
penmates=4
varA=1250
varC=62.5
covAC=-140
varE=4000
sex=20 or -20
The dataset
  Data set:
  Animal Sire Dam Sex Genation Pen Ai Pm1 Pm2 Pm3 adg
20751 10957 13673 2 3 1491 20751 23621 25420 27847 19.22
20752 10957 13673 2 3 1036 20752 23635 28874 29512 19.96
20753 10957 13673 2 3 2327 20753 22409 25602 26703 19.36
20754 10957 13673 2 3 2326 20754 21148 23208 30172 19.57
20755 10957 13673 2 3 2401 20755 22852 28577 29107 19.17
20756 10957 13673 1 3 782 20756 23266 23270 25910 -20.61
20757 10957 13673 1 3 983 20757 20815 21163 29738 -19.87
20758 10957 13673 1 3 1676 20758 21985 22899 23182 -19.31
20759 10957 13673 2 3 421 20759 27356 28702 29785 20.12
20760 10957 13673 2 3 308 20760 23035 29144 29441 18.84

The code used in ASREML:
"Sample to make animal model
Animal !P
Sire !P
Dam !P
Sex 2
Genation 3
Pen 2500
level 4
Ai
Pm1 !P
Pm2 !P
Pm3 !P
adg
ped !MAKE
data !skip1
adg~Sex !r Animal Pm1 -Pm2 and(Pm2) -Pm3 and(Pm3)
0 0 1
Animal 2
2 0 US !GU
0.3125 0 0.016
Animal"
Part of the Output of ".asr" file
"Notice: ASReml assumes Pm1 and and(Pm2)
            have the same levels in the same order.

  Notice: ASReml assumes Pm1 and and(Pm3)
            have the same levels in the same order.
       2 UnStructure 0.3125 0.0000 0.0160
   30750 Ainverse
  Structure for Animal has 61500 levels defined
  Structure for Animal also covers Pm1
  Forming 61502 equations: 2 dense.
  Initial updates will be shrunk by factor 0.316
  Notice: LogL values are reported relative to a base of -40000.000
    1 LogL=-7423.36 S2= 3825.8 9998 df : 1 components
constrained
    2 LogL=-7422.48 S2= 3822.4 9998 df : 1 components
constrained
    3 LogL=-7421.96 S2= 3816.8 9998 df : 1 components
constrained
    4 LogL=-7421.32 S2= 3812.6 9998 df
    5 LogL=-7402.47 S2= 3845.0 9998 df
    6 LogL=-7400.68 S2= 3772.3 9998 df
    7 LogL=-7400.65 S2= 3760.0 9998 df
    8 LogL=-7400.65 S2= 3759.4 9998 df

  Source Model terms Gamma Component Comp/SE % C
  Variance 10000 9998 1.00000 3759.41 38.44 0 P
  Animal UnStructured 1 1 0.337645 1269.35 10.64 0 U
  Animal UnStructured 2 1 -0.399584E-01 -150.220 -5.98 0 U
  Animal UnStructured 2 2 0.174257E-01 65.5104 4.72 0 U
  Covariance/Variance/Correlation Matrix UnStructured Animal
    1269. -0.5209
   -150.2 65.51

  Analysis of Variance NumDF F_inc
    4 Sex 2 366.27

                      Estimate Standard Error T-value T-prev
    4 Sex
                     1 -18.8178 2.50154 -7.52
                     2 18.1941 2.50098 7.27 27.07
    1 Animal 30750 effects fitted ( 1018
are zero)
    9 Pm1 30750 effects fitted ( 1018
are zero)"
Received on Fri Dec 10 2007 - 11:34:03 EST