predict.mixturecure {hdcuremodels}

Predicted probabilities for susceptibles, linear predictor for latency, and risk class for latency for mixture cure fit

Description

This function returns a list the includes the predicted probabilities for susceptibles as well as the linear predictor for the latency distribution and a dichotomous risk for latency for a curegmifs, cureem, cv_curegmifs or cv_cureem fitted object.

Usage

## S3 method for class 'mixturecure'
predict(object, newdata, model.select = "AIC", ...)

Arguments

object

a mixturecure object resulting from curegmifs, cureem, cv_curegmifs, cv_cureem.

newdata

an optional data.frame that minimally includes the incidence and/or latency variables to use for predicting the response. If omitted, the training data are used.

model.select

for models fit using curegmifs or cureem any step along the solution path can be selected. The default is model.select = "AIC" which calculates the predicted values using the coefficients from the model having the lowest AIC. Other options are model.select = "mAIC" for the modified AIC, model.select = "cAIC" for the corrected AIC, model.select = "BIC", model.select = "mBIC" for the modified BIC, model.select = "EBIC" for the extended BIC, model.select = "logLik" for the step that maximizes the log-likelihood, or any numeric value from the solution path. This option has no effect for objects fit using cv_curegmifs or cv_cureem.

...

other arguments

Value

p.uncured

a vector of probabilities from the incidence portion of the fitted model representing the P(uncured).

linear.latency

a vector for the linear predictor from the latency portion of the model.

latency.risk

a dichotomous class representing low (below the median) versus high risk for the latency portion of the model.

See Also

curegmifs, cureem, coef.mixturecure, summary.mixturecure, plot.mixturecure

Examples

library(survival)
set.seed(1234)
temp <- generate_cure_data(N = 100, J = 10, nTrue = 10, A = 1.8)
training <- temp$Training
fit <- curegmifs(Surv(Time, Censor) ~ .,
                  data = training, x.latency = training,
                  model = "weibull", thresh = 1e-4, maxit = 2000,
                  epsilon = 0.01, verbose = FALSE)
predict.train <- predict(fit)
names(predict.train)
testing <- temp$Testing
predict.test <- predict(fit, newdata = testing)