predict.fahrmeier_94: Predict function for the result of `ddhazard`

Description

Predict function for the result of ddhazard

Usage

"predict"(object, new_data, type = c("response", "term"), tstart = "start", tstop = "stop", use_parallel = F, sds = F, max_threads = getOption("ddhazard_max_threads"), ...)

Arguments

object

Result of a ddhazard call

new_data

New data to base predictions on

type

Either "response" for predicted probability of death or "term" for predicted terms in the linear predictor

tstart

Name of the start time column in new_data. It must corresponds to tstart used in the Surv(tstart, tstop, event) in the formula passed to ddhazard

tstop

same as tstart for the stop argument

use_parallel

TRUE if computation for type = "response" should be computed in parallel with the parallel package

sds

TRUE if point wise standard deviation should be computed. Convenient if you use functions like ns and you only want one term per term in the right hand site of the formula used in ddhazard

max_threads

Maximum number of threads to use. -1 if it should be determined by a call to detectCores

...

Not used

Term

The result of type = "term" is a list with the following elements

terms

Is a 3D array. The first dimension is the number of bins, the second dimension is rows in new_data and the last dimension is the state space terms

sds

Similar to terms for the point wise confidence intervals using the smoothed co-variance matrices

Response

The result of type = "response" is a list with the elements below. The function check if there are columns in new_data which's names match tstart and tstop. If not, then each row in new data will get a predicted probability of dying in every bin.

fits

Fitted probability of dying

istart

Vector with the index of the first bin the elements in fits is in