Multi-trait GBLUP via vec-stacked mixed-model equations

Usage

morie_multi_trait_gblup(x, y, markers, Sigma_g = NULL, Sigma_e = NULL)

Arguments

x: Fixed-effect design (vector or matrix).
y: Multi-trait response (n x t).
markers: Genotype matrix (n x m).
Sigma_g: Optional t x t genetic covariance.
Sigma_e: Optional t x t residual covariance.

Value

list(estimate, G_hat, B_hat, Sigma_g, Sigma_e, n, t, method).

References

Montesinos Lopez Ch 10.

Examples

morie_multi_trait_gblup(
  x = rnorm(50), y = rnorm(50),
  markers = matrix(sample(0:2, 200, TRUE), 50, 4)
)
#> $estimate
#> [1] -8.437966e-17
#> 
#> $G_hat
#>              [,1]
#>  [1,] -0.08792781
#>  [2,] -0.19133277
#>  [3,]  0.06932797
#>  [4,] -0.11517442
#>  [5,] -0.26254458
#>  [6,]  0.20988984
#>  [7,]  0.29752696
#>  [8,] -0.24584838
#>  [9,] -0.26748841
#> [10,]  0.13960939
#> [11,]  0.29752736
#> [12,]  0.13466368
#> [13,]  0.20989139
#> [14,] -0.18144115
#> [15,] -0.18545584
#> [16,] -0.25172272
#> [17,] -0.25759716
#> [18,] -0.19133324
#> [19,]  0.12384219
#> [20,] -0.25172102
#> [21,]  0.20494593
#> [22,]  0.04768796
#> [23,]  0.36873785
#> [24,] -0.25666921
#> [25,]  0.37862933
#> [26,]  0.12971860
#> [27,]  0.04768799
#> [28,]  0.23219281
#> [29,] -0.01671739
#> [30,] -0.19133029
#> [31,] -0.08792935
#> [32,]  0.05943982
#> [33,] -0.40805144
#> [34,] -0.25666706
#> [35,] -0.25172202
#> [36,]  0.20988874
#> [37,]  0.12384354
#> [38,]  0.30340341
#> [39,]  0.37955942
#> [40,]  0.36780813
#> [41,]  0.13466318
#> [42,] -0.18638626
#> [43,]  0.20000070
#> [44,]  0.05757704
#> [45,] -0.09287738
#> [46,]  0.29258251
#> [47,] -0.25760014
#> [48,] -0.32787936
#> [49,]  0.12971853
#> [50,] -0.32694689
#> 
#> $B_hat
#>             [,1]
#> [1,] -0.08792641
#> [2,] -0.22874406
#> 
#> $Sigma_g
#>           [,1]
#> [1,] 0.6027952
#> 
#> $Sigma_e
#>           [,1]
#> [1,] 0.6027952
#> 
#> $n
#> [1] 50
#> 
#> $t
#> [1] 1
#> 
#> $method
#> [1] "Multi-trait GBLUP (vec-stacked MME)"
#>