Differences

This shows you the differences between two versions of the page.

--- covariance_structure_of_correlated_random_effects_for_multiple_traits [2018/03/29 18:52] – andres
+++ covariance_structure_of_correlated_random_effects_for_multiple_traits [2018/03/29 18:54] – andres
@@ Line 3: / Line 3: @@
 For instance terminal crosses models (e.g. [[https://gsejournal.biomedcentral.com/articles/10.1186/s12711-016-0211-3||here]]) use:
-  * trait_pure: **y = u + e** (animal)
+  * trait_pure: **y = hys u + e** (animal)
-  * trait_crossbred : **y = s + e** (sire of crossbred)
+  * trait_crossbred : **y = hys s + e** (sire of crossbred)
-Thus we have two traits, purebred and crossbred performance, but effect **u** only affects purebreds and effect **s** only affects crossbreds. Data file has "animal" in column 4 and "sire" in column 5.
+Thus we have two traits, purebred and crossbred performance, but effect **u** only affects purebreds and effect **s** only affects crossbreds. Data file has "animal" in column 4 and "sire" in column 5. Effect **hys** has respectively 12 and 25 levels.
 <file>
-...
+0  12 cross
+2  25 cross
 0  3084 cross
 5  3084 cross
 ...
 RANDOM_GROUP
- 5
+ 4
 RANDOM_TYPE
 add_animal
@@ Line 27: / Line 28: @@
 Where we have a 4x4 matrix for covariances. In fact this corresponds to
-^      ^	^Effect 4^Effect 4^Effect 5^Effect 5|
+^      ^	^Effect 3^Effect 3^Effect 4^Effect 4|
 ^      ^	^Trait 1 ^Trait2^Trait1	 ^Trait2|
-^Effect 4^Trait 1|Var(u)|     0 |	0|Cov(u,s)|
+^Effect 3^Trait 1|Var(u)|     0 |	0|Cov(u,s)|
-^Effect 4^Trait 2 |0	|     0 |	0|	0|
+^Effect 3^Trait 2 |0	|     0 |	0|	0|
-^Effect 5^Trait 1|0	|     0 |      0|	0|
+^Effect 4^Trait 1|0	|     0 |      0|	0|
-^Effect 5^Trait 2|Cov(s,u)|	0|	0|Var(s)|
+^Effect 4^Trait 2|Cov(s,u)|	0|	0|Var(s)|