predict.aftree: Estimating the survival and the hazard for AFT BART models.

Description

The function predict.aftree() is provided for performing posterior inference via test data set estimates stored in a aftree object returned from AFTree() in a similar fashion as that of predict.nft. N.B. the x.test matrix must be provided on the AFTree() function call. Here we are only calculating the survival function by default, and, if requested, the hazard as well.

Usage

# S3 method for aftree
predict(
            ## data
            object,
            ## predictions
            events=NULL,
            FPD=FALSE,
            probs=c(0.025, 0.975),
            take.logs=TRUE,
            seed=NULL,
            ## default settings
            ndpost=nrow(object$mix.prop),
            nclust=ncol(object$mix.prop),
            ## etc.
            ...)

Value

surv.fpd: Survival function posterior draws on a grid of time-points by the partial dependence function when requested.
surv.fpd.mean: Survival function estimates on a grid of time-points by the partial dependence function when requested.
surv.fpd.lower: Survival function lower quantiles on a grid of time-points by the partial dependence function when requested.
surv.fpd.upper: Survival function upper quantiles on a grid of time-points by the partial dependence function when requested.

Arguments

object: Object of type nft from a previous call to nft().
events: You must specify a grid of time-points; however, they can be a matrix with rows for each subject.
FPD: Whether to yield the usual predictions or marginal predictions calculated by the partial dependence function.

probs: A vector of length two containing the lower and upper quantiles to be calculated for the predictions.
take.logs: Whether or not to take logarithms.
seed: If provided, then this value is used to generate random natural logarithms of event times from the predictive distribution.
ndpost: The number of MCMC samples generated.
nclust: The number of DPM clusters generated.
...: The et cetera objects passed to the predict method. Currently, it has no functionality.

Author

Rodney Sparapani: rsparapa@mcw.edu

Details