Poisson loss for count outcomes

Formula: L(w) = sum_i sum_j [ yhat_ij - y_ij log(yhat_ij) ]

Usage

Poislo(Y, Yhat)

Arguments

Y

Observed counts; a flat vector is read as one column.

Yhat

Predicted Poisson means, strictly positive.

Value

List with loss, mean_loss, n, L.

References

Montesinos Lopez, Montesinos Lopez and Crossa (2022), Multivariate Statistical Machine Learning Methods for Genomic Prediction, Springer, doi:10.1007/978-3-030-89010-0. Chapter 10, Sect. 10.7, pp. 400-403. Read from the chapter PDF, not recalled. The Poisson display carries its sign correctly and is implemented exactly as printed.

Examples

V <- c(1, 2, 3, 4, 5, 6, 7, 8)
Poislo(V, V)
#> $loss
#> [1] -23.28196
#> 
#> $mean_loss
#> [1] -2.910245
#> 
#> $n
#> [1] 8
#> 
#> $L
#> [1] 1
#> 
#> $method
#> [1] "Poisson loss, MVSML Sect. 10.7.2"
#> 
#> attr(,"class")
#> [1] "morie_rich_result" "list"