SL.gwqs: SLMix package

In alexpkeil1/SLmix: Extensions of Bayesian Kernel Machine Regression and Weighted Quantile Sums for prediction and integration with SuperLearner package

Usage

SL.gwqs(Y, X, newX, family, obsWeights, id, b = 20, q = 4, validation = 0, ...)

Arguments

Y
X
newX
family
obsWeights
id
b
q
validation
...

Examples

##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

## The function is currently defined as
function (Y, X, newX, family, obsWeights, id, b = 20, q = 4, 
    validation = 0, ...) 
{
    nm = names(X)
    if (is.matrix(X)) {
        X = as.data.frame(X)
    }
    if (is.matrix(newX)) {
        newX = as.data.frame(newX)
    }
    X$Y = Y
    if (family$family == "gaussian") {
        gwqsfit = my.gwqs(Y ~ NULL, mix_name = nm, data = X, 
            q = q, b = b, b1_pos = TRUE, family = "gaussian")
    }
    if (family$family == "binomial") {
        gwqsfit = my.gwqs(Y ~ NULL, mix_name = nm, data = X, 
            q = q, b = b, b1_pos = TRUE, family = "binomial")
    }
    pred <- predict.my.gwqs(fit = gwqsfit, mix_name = nm, newdata = newX)
    class(gwqsfit) <- c("SL.gwqs")
    out <- list(pred = pred, fit = gwqsfit)
    return(out)
  }

alexpkeil1/SLmix documentation built on Aug. 15, 2020, 9:10 a.m.