Nonparametric links of the zero-altered Poisson forest

Formula: log(mu) = f_mu(x) and log(theta/(1-theta)) = f_theta(x) (eq. 15.1): under ZAP_RF and ZAPC_RF the links between covariates and response are general nonparametric functions estimated by two random forests rather than linear predictors.

Usage

Msm323(mu_pred, theta_pred)

Arguments

mu_pred

Forest prediction on the log-mean scale.

theta_pred

Forest prediction on the logit scale.

Value

List with estimate, mu, theta, method.

References

Montesinos Lopez, Montesinos Lopez & Crossa (2022), Multivariate Statistical Machine Learning Methods for Genomic Prediction, Springer, eq. (15.1) p.651. DOI 10.1007/978-3-030-89010-0.

Examples

# forest predictions on the log-mean and logit scales
Msm323(mu_pred = log(c(1.5, 3, 0.8)), theta_pred = qlogis(c(0.2, 0.5, 0.7)))
#> $estimate
#> [1] 0.8
#> 
#> $mu
#> [1] 0.8
#> 
#> $theta
#> [1] 0.2 0.5 0.7
#> 
#> $method
#> [1] "ZAP nonparametric links (MVSML 2022 eq. 15.1)"
#>