predict.gfcure {gfcure}

R Documentation

Predictions from a fitted accelerated failure time mixture cure model.

Description

Predict survival probabilities and cure rates based on gfcure object

Usage

## S3 method for class 'gfcure'
predict(object, newtime = unique(sort(object$y[, 1])),
  newdata = NULL, conf.int = 0.95)

Arguments

object	Object of class inheriting from "gfcure"
newtime	An optional vector of time points at which the survival probability is to be predicted. If omitted, the time points in the original data are used.
newdata	A data frame in which to look for variables with which to predict.
conf.int	Confidence level for confidence interval estimates

Details

"predict.gfcure" produces predicted survival probabilities, cure rates and their confidence intervals, obtained by evaluating the regression function in the frame "newdata".

Value

"predict.gfcure" produces a list of predictions

pred	a list of predict survival probabilities, cure rates and its confidence intervals
time	a vector of time points at which the survival probabilities are calculated
class	a predict.gfcure class is defined

Author(s)

Yingwei Peng

References

Peng, Y., Dear, K.B.G. and Denham, J. W. "A generalized F mixture model for cure rate estimation," Statistics in Medicine 17, 813–830 (1998).

See Also

See Also as predict

Examples

z = gfcure(Surv(time, cens) ~ x1, ~ x1, data = simdata)
predict(z, newdata = simdata[1, ])

---