Differences

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

--- readme.pedictf90 [2020/03/13 19:05] – yutaka
+++ readme.pedictf90 [2022/05/09 22:38] – [Example] dani
@@ Line 12: / Line 12: @@
   * residual = y - included effects (not a true residual)
-==== More explanation ====
+==== Example ====
-This program splits the phenotype (y) into 3 pieces.
+For instance consider
-  y = (effects to be corrected) + (effects to keep) + residual
+  y = herd + age + animal + e
-In a cross validation, you need a quantity "y_star = EBV + residual", and EBV is ''(effects to keep)'' shown above.
+with ''OPTION include_effects 3''.
-Therefore, you should need ''y_star'' as ''y - (effects to be corrected)''.
-The program calculates the following quantities.
-  * y_hat: ''(effects to keep)''
+  * ystar = y - herd_hat - age_hat
-  * y_star: ''y - (effects to be corrected)''
+  * y_hat = animal_hat
-  * residual: ''residual''
+Which makes cor(y_hat,y_star) = cor(ebv, adjusted y), in this example, which is a measure of accuracy.
-=== Example ===
+It outputs the correlation between y_hat and y_star, for instance, cor(ystar,yhat)=cor(u+e, uhat) and outputs these columns into a file, together with animal id (if there is animal in the model) or record number (if not).
-For instance consider
+In addition, if animal effect is in the model, it produces a file with ebvs from the solutions file.
-  y = herd + age + animal + e
+==== More explanation ====
-with ''OPTION include_effects 3''.
+This program splits the phenotype (y) into 3 pieces.
-  * y_hat = animal_hat
+  y = (effects to be corrected) + (effects to be kept) + residual
-  * ystar = y - herd_hat - age_hat
-Which makes cor(y_hat,y_star) = cor(ebv, corrected y) which is a measure of accuracy.
+In a cross validation, you need a quantity "EBV + residual", where EBV is ''(effects to be kept)'' shown above, and it is ''y_star''.
+The program calculates the following quantities.
-It outputs the correlation between y_hat and y_star, for instance cor(ystar,yhat)=cor(u+e, uhat) and outputs these columns into a file, together with animal id (if there is animal in the model) or record number (if not).
+  * y_hat: ''(effects to kept)''
+  * y_star: ''y - (effects to be corrected)''
+  * residual: ''residual''
-In addition, if animal effect is in the model, it produces a file with ebvs from the solutions file.
+The user should specify the effects to be kept using ''OPTION include_effects'' with the effect numbers.
+For example, if the breeding value is in the 3rd row in the EFFECTS section in the parameter file, you have to use ''OPTION include_effects 3''.
 ==== Output files ====