SL.coxph: Cox proportional hazard regression models back-transformed to...
In wuziyueemory/twostageSL: Two-Stage Super Learner Prediction Function

Description Usage Arguments Value References Examples

This function implements Cox proportional hazard regression models (David 1972), and back-transforms to the conditional mean scale (see also Basu 2005).

1	SL.coxph(Y, X, newX, family, obsWeights, ...)

`Y`	A numeric outcome variable
`X`	A `data.frame` of covariates constituting the training sample
`newX`	A `data.frame` with the same column names and format as `X` constituting the validation sample.
`family`	Gaussian only
`obsWeights`	Observation-level weights (not currently used)
`...`	Other arguments (unused)

pred: Predicted outcomes based on predictors in newX
fit: A list with named entries object (the fitted coxph model object), randomUpper.

Basu A and Rathouz PJ. Estimating marginal and incremental effects on health outcomes using flexible link and variance function models. Biostatistics 2005; 6(1): 93–109.

# load cost data
data(cost_data)
# fit cox ph model
fit_coxph <- SL.coxph(Y = cost_data$totalcost, X = cost_data[, c("female", "race")],
                              newX = cost_data[, c("female", "race")])
# get back predictions
pred_coxph <- predict(fit_coxph$fit, newdata = cost_data[,c("female", "race")])